CU-MBA-SEM-IV-Marketing Analytics

New tools come up every month and with this, come challenges to integrate that tool and its performance numbers with the rest of your marketing tools. With this in mind, here are the 6 Steps to creating an effective marketing dashboard: 1. Determine your Audience: To build an effective dashboard the most important step is to define your audience. Data Dashboards and Data Visualization, in general, is designed to tell a story, so you need to know who is listening to your story. A well-designed dashboard tells a compelling story that links to actionable KPIs that benefit the viewer. Different audiences will require different dashboards. An executive needs a dashboard that summarizes performance metrics so they can make informed business decisions; a dashboard for a social media marketer will need a social media dashboard to consolidate all metrics from sites like Twitter, Facebook, Google+, LinkedIn, so they can get detailed data on key social metrics. We’ve even created social media info graphic to aid social media marketers as they craft and visualize their key metrics. Suffice it to say; depending on your particular position within a marketing agency, you could be tracking entirely different KPIs. 2. Set Objectives of your Stakeholders: Different Marketing dashboards can tell a different story and it is important to establish the objectives of each of your dashboards. Determine short-term and long-term objectives of your stakeholders and build different views of data at different levels of granularity. As an example, an executive might want to look at a high-level dashboard that provides an overall return on investment and budget. If you’re interested in executive dashboards, we’ve written an executive dashboard guide to provide even deeper insight into proper visualization. An analyst, on the other hand, will want a detailed view of the data to take tactical decisions. An important thing to remember while creating Marketing Performance Dashboards for your stakeholders is to tell a powerful story that provides a path for immediate action. The goal isn’t to visualize data because it looks cool. The goal is to understand your data better. Provide insights and connections between various elements of your marketing strategy to demonstrate ROI and opportunities for improvement. 3. Determine Marketing KPIs: It is important to determine what metrics are important for your specific marketing strategy (and it’s even more important as an agency to understand what strategy to use). These KPIs can include marketing performance metrics of each program or campaign such as likes, clicks, dwell time, traffic, click through rate, etc. A KPI can also include the marketing impact metrics that tie performance to business goals like conversions, increase in brand value or increase in sales. These KPIs once identified can be analyzed across various dimensions like date and source of data so you can provide insights to your team and to the heads of marketing. Determining your marketing KPI is important as it allows for you to track and convey your own value and the value of your team’s efforts in the areas that matter. 151 CU IDOL SELF LEARNING MATERIAL (SLM)

You could be getting tons of clicks, but are clicks key performance indicators? It all depends on your particular role within the company and your particular objective in a marketing campaign. Don’t copy and paste the same KPIs for every marketing effort. Tailor your analytics dashboard to the personalized KPIs of each marketing campaign (campaigns can often have the same KPIs but not always). 4. Determine Data Sources and How to Provide a Unified View: New marketing platforms have made it easier for business owners and marketing teams to manage everything from their website, email marketing, and call tracking, to their social media strategy. Each of these data sources will have their own set of metrics and data and it is important to consolidate them to a single platform to easily measure the performance of marketing programs. With all of this data, it’s tempting to include everything in one dashboard. Pro Tip: Don’t be guilty of information overload. Determine the metrics that matter and the data sources you want to use to gather the defined metrics. 152 CU IDOL SELF LEARNING MATERIAL (SLM)

Fig. 10.3 5. Visualize your Data: Marketing Analytics tools can provide you with countless amounts of data and it’s important that you convey the right message (because your visuals can easily convey a message you haven’t intended to convey) with your marketing analytics dashboard. Make sure it’s easy for everyone on your marketing team to create and consume data that encourages data discovery and analysis. The real value in visualizing all of your marketing data is that you’ve given your marketing team the tools that are necessary for understanding all of this data while enabling yourself to find additional insights that may not be found if the data was kept in its nascient CSV format. 6. Data Integration: 153 CU IDOL SELF LEARNING MATERIAL (SLM)

Today a marketing team uses hundreds of tools that contain a myriad of metrics. A very important objective of any analytics dashboard is to consolidate and integrate data into a consistent view using some sort of visualization tool. A consolidated marketing dashboard should combine these multiple data sources into a single source that should also be connected to outcomes and ROI. Make sure you use a tool that can integrate all of your data. You miss out on the immense value of data visualization if you don’t have reporting tools capable of weaving together the right story and you’re missing chapters in your book if you leave out important data sources simply because you haven’t integrated all of your data. We hope this small guide helps you with your marketing dashboards. Tap Clicks has a ton of resources on our blog. Check out more of our marketing dashboard guides if you’re trying to get a more detailed description on best practices for certain kinds of marketing campaign visualizations. New tools come up every month and with this, come challenges to integrate that tool and its performance numbers with the rest of your marketing tools. With this in mind, here are the 6 Steps to creating an effective marketing dashboard: 1. Determine your Audience: To build an effective dashboard the most important step is to define your audience. Data Dashboards and Data Visualization, in general, is designed to tell a story, so you need to know who is listening to your story. A well-designed dashboard tells a compelling story that links to actionable KPIs that benefit the viewer. Different audiences will require different dashboards. An executive needs a dashboard that summarizes performance metrics so they can make informed business decisions; a dashboard for a social media marketer will need a social media dashboard to consolidate all metrics from sites like Twitter, Facebook, Google+, LinkedIn, so they can get detailed data on key social metrics. We’ve even created social media info graphic to aid social media marketers as they craft and visualize their key metrics. Suffice it to say; depending on your particular position within a marketing agency, you could be tracking entirely different KPIs. 2. Set Objectives of your Stakeholders: Different Marketing dashboards can tell a different story and it is important to establish the objectives of each of your dashboards. Determine short-term and long-term objectives of your stakeholders and build different views of data at different levels of granularity. As an example, an executive might want to look at a high-level dashboard that provides an overall return on investment and budget. If you’re interested in executive dashboards, we’ve written an executive dashboard guide to provide even deeper insight into proper visualization. An analyst, on the other hand, will want a detailed view of the data to take tactical decisions. An important thing to remember while creating Marketing Performance Dashboards for your stakeholders is to tell a powerful story that provides a path for immediate action. The goal isn’t to visualize data because it looks cool. The goal is to understand your data better. 154 CU IDOL SELF LEARNING MATERIAL (SLM)

Provide insights and connections between various elements of your marketing strategy to demonstrate ROI and opportunities for improvement. 3. Determine Marketing KPIs: It is important to determine what metrics are important for your specific marketing strategy (and it’s even more important as an agency to understand what strategy to use). These KPIs can include marketing performance metrics of each program or campaign such as likes, clicks, dwell time, traffic, click through rate, etc. A KPI can also include the marketing impact metrics that tie performance to business goals like conversions, increase in brand value or increase in sales. These KPIs once identified can be analyzed across various dimensions like date and source of data so you can provide insights to your team and to the heads of marketing. Determining your marketing KPI is important as it allows for you to track and convey your own value and the value of your team’s efforts in the areas that matter. You could be getting tons of clicks, but are clicks key performance indicators? It all depends on your particular role within the company and your particular objective in a marketing campaign. Don’t copy and paste the same KPIs for every marketing effort. Tailor your analytics dashboard to the personalized KPIs of each marketing campaign (campaigns can often have the same KPIs but not always). 4. Determine Data Sources and How to Provide a Unified View: New marketing platforms have made it easier for business owners and marketing teams to manage everything from their website, email marketing, and call tracking, to their social media strategy. Each of these data sources will have their own set of metrics and data and it is important to consolidate them to a single platform to easily measure the performance of marketing programs. With all of this data, it’s tempting to include everything in one dashboard. Pro Tip: Don’t be guilty of information overload. Determine the metrics that matter and the data sources you want to use to gather the defined metrics. 5. Visualize your Data: Marketing Analytics tools can provide you with countless amounts of data and it’s important that you convey the right message (because your visuals can easily convey a message you haven’t intended to convey) with your marketing analytics dashboard. Make sure it’s easy for everyone on your marketing team to create and consume data that encourages data discovery and analysis. The real value in visualizing all of your marketing data is that you’ve given your marketing team the tools that are necessary for understanding all of this data while enabling yourself to find additional insights that may not be found if the data was kept in its nascient CSV format. 6. Data Integration: Today a marketing team uses hundreds of tools that contain a myriad of metrics. A very important objective of any analytics dashboard is to consolidate and integrate data into a 155 CU IDOL SELF LEARNING MATERIAL (SLM)

consistent view using some sort of visualization tool. A consolidated marketing dashboard should combine these multiple data sources into a single source that should also be connected to outcomes and ROI. Make sure you use a tool that can integrate all of your data. You miss out on the immense value of data visualization if you don’t have reporting tools capable of weaving together the right story and you’re missing chapters in your book if you leave out important data sources simply because you haven’t integrated all of your data. We hope this small guide helps you with your marketing dashboards. Tap Clicks has a ton of resources on our blog. Check out more of our marketing dashboard guides if you’re trying to get a more detailed description on best practices for certain kinds of marketing campaign visualizations. 10.6 BENEFITS OF MARKETING DASHBOARDS A dashboard has many functions, so there are a number of benefits of dashboard reporting. Here are the top six features and benefits of a dashboard: 1. Data transparency – Data is any company’s most important asset. However, it doesn’t do much good if no one can understand or access it. A well-designed dashboard provides on-demand access of all of your most important metrics. 2. Access to data – As the name implies, a dashboard gathers multiple data sources, including Excel, into a single interface. That means you can immediately see a detailed overview of your business in one quick glance. Better yet, it reduces the amount of time it takes to compile reports, saving you time. 3. Better decision making – Dashboards provide an unbiased view not only of the company’s performance overall, but each department as well. If each department is able to access the dashboard, it can offer a foundation for further dialogue and great decision making. For example, the sales and marketing department can align their data and experiences to increase customer acquisitions and improve demand generation. Business dashboards provide a good starting point for these decisions, which is one of the biggest advantages of dashboards. 4. Accountability – While it’s always nice to see what you’re doing right, you also need to see and understand what you’re doing wrong in order to increase your performance. Business dashboards can show you exactly where your trouble areas are and arm you with the information you need to improve. Also, by making the dashboards visible throughout the company, they can hold different departments accountable for both the ups and downs. 5. Interactivity – Some of the best dashboards provide a dynamic experience. Rather than providing static information, you and your users can filter data, interact with charts to see changes over time, and even allow for an ad-hoc component for on-the- fly. That means you can get as much or as little detail on specific metrics as you want. 156 CU IDOL SELF LEARNING MATERIAL (SLM)

6. Gamification – Your metrics, whether traffic to your website or products sold, are the key numbers you want to continuously improve upon. The top businesses have managed to gamify certain business metrics to increase the likelihood of customer retention. If you’re considering gamification, business dashboards can track the success of your efforts. The top metrics for modern marketing teams:  Customer Conversion Rates.  Brand awareness.  Customer engagement.  Marketing spends per customer.  Return on marketing expenditure &investment.  Lifetime retention of a customer (LTV)  Customer acquisition cost (CAC)  Customer retention. 10.7 SUMMARY A dashboard makes it so much easier to comprehend what’s happening with your marketing, and it enables speedier decision-making. A great marketing dashboard will meet the 5-1-5 Rule. A user should be able to visualize in 5 seconds, develop an insight within sixty seconds or minute and be able to make a business decision within 5 minutes. And while marketing dashboards make data simpler to understand, they don’t necessarily dumb it down. Because of their interactive nature, a dashboard allows users to explore exponentially greater volumes of data and ask better questions, on their own, than a typical spread sheet could. Benefits of a BI dashboard  Enhanced visibility. ...  Timesaving efficiency. ...  Better forecasting. ...  Key performance indicators. ...  Inventory control. ...  Real-time customer analytics. ...  Better decision-making. Here are 10 KPIs every business should be measuring:  Sales Revenue. ... 157 CU IDOL SELF LEARNING MATERIAL (SLM)

 Cost Associated Per Lead Acquisitions. ...  Customer Lifetime Value. ...  Online Marketing ROI. ...  Site Traffic: Lead Ratio. ...  Marketing Qualified Leads: Sales Qualified Leads. ...  Form Conversion Rates. ...  Organic Search. 10.8 KEYWORDS  Dashboards: - are data visualization tools that allow all users to understand the analytics that matter to their business, department or project.  KPI: - Key Performance Indicator  ROI: - Return on Investment  SEO: - Search Engine Optimization  CAC: - Customer Acquisition Cost... cost spent for customer acquiring 10.9 LEARNING ACTIVITY 1. What are Marketing Dashboards? ___________________________________________________________________________ _____________________________________________________________________ 2. Define is the importance of Marketing Dashboards? ___________________________________________________________________________ _____________________________________________________________________ 3. How do you approach Marketing Data Dashboards? ___________________________________________________________________________ _______________________________________________________________ 10.10 UNIT END QUESTIONS A. Descriptive Questions Short Questions 1. Define Marketing Analytics Dashboards 2. What is purpose of Marketing Dashboards? 3. What are the Marketing Analytics? 158 CU IDOL SELF LEARNING MATERIAL (SLM)

4. Explain the rules for creating Marketing Dashboards 159 5. Explain importance of Marketing Dashboards in Business Development. Long Questions 1. What is Marketing Dashboards Approach? 2. Explain difference between Slicing & Dicing 3. What should be on a Marketing Dashboards? 4. How do you describe a Dashboard? 5. What is the importance of Customer Data Analysis? B. Multiple choice Questions 1. Marketing Analytics Dashboard is for ________ a. Product b. Customer Data Analysis c. Customer Meet d. Test Marketing 2. Dashboards are very useful in ___________ a. Google Analytics b. Market Survey c. Customer & Data Analysis d. Marketing Analytics 3. Marketing Dashboards should include _________ a. Each Lead & Website visit b. Direct Sales Report c. Marketing Feedback d. Customer Complaints 4. ________ is the main indicator of Business a. Sales Analysis b. Digital Marketing CU IDOL SELF LEARNING MATERIAL (SLM)

c. ROI d. Product Development 5. The main objective of Marketingis _____________ a. Marketing Planning b. Customer & Competition c. Conversion d. Sales Reports Answers 1-b, 2-a, 3-a, 4-c, 5-b. 10.11 REFERENCES Textbooks  T1 Grigsby, M. 2115. Marketing Analytics: A practical guide to real marketing science, Its Ed., Kogan Page, India, ISBN: 978-0749474171.  T2 Winston, W. 2114.Marketing Analytics: Data Driven Technique using MS. Excel. Ist Ed. John Wiley & Sons, India, ISBN: 978-1118373439. Reference Books:  R1 Grigsby, M. 2116. Advanced Customer Analytics: Targeting, Valuing, Segmenting and Loyalty Techniques (Marketing Science). Ist Ed. Kogan Page. India. ISBN: 978-0749477158. Websites  https://springer.com  https://michaelpawlicki.com  https://statisticshowto.com  https://stattrek.com  https://slideshare.com 160 CU IDOL SELF LEARNING MATERIAL (SLM)

UNIT 11: REGRESSION ANALYSIS, MARKET BASKET ANALYSIS STRUCTURE 11.0 Learning Objectives 11.1 Introduction of Regression Analysis 11.2 Definitions of Regression Analysis 11.3 Objectives of Regression Analysis 11.4 Models of Regression Analysis 11.5 Steps involved in Regression Analysis 11.6 Introduction of Market Basket Analytic 11.7 Application of Market Basket Analytics 11.8 Summary 11.9 Keywords 11.10 Learning Activity 11.11 Unit End Questions 11.12 References 11.0 LEARNING OBJECTIVES Why Is It Important? Regression has a huge range of real-life business & marketing applications. It is essential for any new or old machine learning problem that consists of continuous numbers – this includes, but is not limited to, a host of examples, including:  Finance / cost forecasting (like house price estimates, or material prices)  Sales and promotions forecasting  Testing automobiles  Weather analysis and prediction  Time series forecasting Regression analysis is used when you want to predict a continuous dependent variable from a number of various independent variables. ... Independent variables with more than two levels or multiple can also be used in regression analyses, but they first must be converted into variables that have only two levels. CU IDOL SELF LEARNING MATERIAL (SLM)

11.1 INTRODUCTION REGRESSION ANALYSIS Regression analysis is used when you want to predict a continuous dependent variable from a number of independent variables. Independent variables with more than two levels can also be used in regression analyses, but they first must be converted into variables that have only two levels. Regression analysis is the method of using observations (data records) to quantify the relationship between a target variable (a field in the record set), also referred to as a dependent variable and a set of independent variables, and also referred to as a covariate  Regression is a statistical method used in finance, investing, and other disciplines that attempts to determine the strength and character of the relationship between one dependent variable (usually denoted by Y) and a series of other variables (known as independent variables).  Regression helps investment and financial managers to value assets and study the relationships between variables, such as commodity prices and the stocks of businesses dealing in those commodities. 11.2 DEFINIATION OF REGRESSION ANALYSIS  Regression analysis is used when business wishes to predict a continuous dependent variable from a number of independent variables. ... Independent variables with more than two levels can also be used in regression analyses, but they first must be converted into variables that have only two levels.  Regression analysis is used when you want to predict a continuous dependent variable from a number of independent variables. ... Independent variables with more than two levels can also be used in regression analyses, but they first must be converted into variables that have only two levels.  Regression analysis is a way of mathematically sorting out which of those variables does indeed have an impact. It answers the questions: Which factors matter most? Which can we ignore? How do those factors interact with each other? And, perhaps most importantly, how certain are we about all of these factors? In regression analysis, those factors are called variables. You have your dependent variable — the main factor that you’re trying to understand or predict. In Redman’s example above, the dependent variable is monthly sales. And then you have your independent variables — the factors you suspect have an impact on your dependent variable 162 CU IDOL SELF LEARNING MATERIAL (SLM)

11.3 OBJECTIVES OF REGRESSION ANALYSIS Objective of Regression analysis is to explain variability in dependent variable by means of one or more of independent or control variables. The Objective of Regression Analysis Regression analysis is a set of statistical techniques used to evaluate the relationship among variables. A common misconception is that regression analysis is the same as correlation analysis. Correlation analysis is concerned with measuring the association between two variables, whereas regression analysis is focused on understanding if some process can be explained by one or more variables. More specifically, regression analysis is used to determine if the variability in a dependent variable can be explained by one or more independent variables. For this reason, it is important for us to give some thought to which is our dependent variable and which are our independent variables. Once we have figured this out, we can fit one of several types of regression models to our data and make a conclusion about the relationship between variables.  Regression Analysis helps with more inputs with detailed insight that can be applied to further improve products & services  Here at Alchemic, we offer hands-on application training events during which customers learn how to become super users of our software.  The various data collected from these feedback surveys allows us to review the levels of satisfaction that our attendees associate with our events, and what variables influence those levels of satisfaction.  Could it be the topics covered in the individual sessions of the event? The time duration of the sessions? The food or catering services provided? The cost to attend? Any of these variables have the potential to impact an attendee’s level of satisfaction.  By performing a regression analysis on this survey data, we can determine whether or not these variables have impacted overall attendee satisfaction, and if so, to what extent.  This information then informs us about which elements of the sessions are being well received, and where we need to focus attention so that attendees are more satisfied in the future. 11.4 MODELS OF REGRESSION ANALYSIS The Regression Model Once you have determined your dependent and independent variables, you are ready to fit a regression model. The most basic of regression models, and the focus of this section, is an ordinary least squares (OLS) regression. An OLS model operates by fitting a linear line 163 CU IDOL SELF LEARNING MATERIAL (SLM)

through the data that minimizes the squared sum of the residuals (remember that we square the residuals to remove negative values, otherwise our sum of squares would equal 0). The figure below illustrates a set of points for which there is a known X and Y (we also refer to these errors as residuals). The red line is the line of least squares that minimizes the error or difference d, between all points and the line. In other words, no other line can reduce the sum of error from this least squares line. The OLS regression model is defined by the following formula: Thus, any value of Y can be predicted using parameters a and b, and a value of X. While it’s beyond the scope of what we need to know for this course, parameters a and b are calculated as follows: It should be intuitive that b relative to a value of 0 provides the following outcomes: To be a little more formal, we should be referring to parameters a and b as coefficients. Often times we see β0 representing the y-intercept, and β1 representing the slope. Therefore, the formula changes to Y =β0 +β1X1. Next, we add an error term into the formula to include our level of uncertainty in predicting Y, and so our formula becomes Y = β0 + β1X1 + ε. P-values Regression analyses most often produce a p-value, which is very similar to a p-value that is generated when conducting an inferential statistical test such as a difference of means test or a nearest neighbor analysis. Like these other methods, we need to specify a null hypothesis, which in the case of regression analysis states that a coefficient is not significantly different from 0; in other words, the explanatory variable does not aid in explaining the variability in the dependent variable. Small p-values indicate that there is a small probability that a coefficient is 0; explained differently, a small p-value reveals that there is a small probability that a coefficient does not explain the variability in the dependent variable. For example, a p- value of 0.05 would lead one to conclude that a coefficient is statistically significant at the 95% confidence level, and thus the variable is an effective predictor of the dependent variable. R2 Values One of the most sought after outcomes with a regression analysis is a high R2 value. The R2 is referred to as the coefficient of determination, and represents how well the model fits the observed dependent variable. An OLS model with a R2 value of 1.0 means that the model fits the data perfectly, and that the independent variable accounts for 100% of the variability in the dependent variable. It is highly unreasonable to expect a R2 value of or close to 1.0, unless your independent variable is too closely associated with the dependent variable (for example: if you used the number of females per country to predict the number of males per country). Instead, we are more likely to observe R2 values in the lower-to-middle range between the minimum and maximum values of 0 and 1, respectively. 164 CU IDOL SELF LEARNING MATERIAL (SLM)

The important thing to note about the R2 value is this: a regression model with a R2 value of k explains k percent of the variation in the dependent variable. Relatively lower R2 values are not a bad thing; they simply reveal what the model is able to explain about our variable in question. Residuals Each data point in a regression model has a residual that represents the unexplained portion of the dependent variable. A residual is the difference in Y between the observed point and the model. The residual represent the error in the model’s ability to predict Y, and is represented by ε in the OLS formula. Large residuals indicate points that are relatively far from the model, thus the model is not a good predictor at this value of Y. Thus, the magnitude of the residuals is a measure of model fit, where many large residuals will lead to a low R2 value, whereas having all small residuals will lead to a high R2 value. Also note that a positive residual represents an area in the model where the observation has a higher value of Y than what the model estimates, while a negative residual indicates an area where the observation is below the model. Challenges with Standard Regression Models There are four main assumptions that we need to ensure we acknowledge when conducting an OLS regression, each of which refers to the residual error in the model. It is rarely the case that an OLS model perfectly adheres to these assumptions, so instead we treat them as general guidelines to consider when evaluating the suitability and effectiveness of our regression analysis. Assumption 1: The mean of the distribution of ε for any given value of X is Y = β0 +β1X1. This means that, for any value of X, the mean error must equal the regression model. This is illustrated in the figure below, where the average residual for X1, X2, and X3 is located on the OLS regression line. Assumption 2: The variance of ε is Constance across Y = β0+β1X1. This assumption states that there cannot exist greater variability in residuals in one area of the model versus another. Looking at the figure above, this assumption is represented by having the same size error distribution throughout the regression model. Assumption 3: The probability distribution of ε is normal. As the figure above shows, each value of X is associated with a normal distribution of residuals centred on the regression model. Assumption 4: The value of ε associated with one value of Y is independent of all other values of ε. That is, a residual for one observation should not influence the residual for any other observation. How do we tell if our regression analysis abides by these assumptions? As geographers, we are interested to interrogate these assumptions from a spatial perspective; therefore it is 165 CU IDOL SELF LEARNING MATERIAL (SLM)

important to analyze the spatial distribution of the errors. By mapping the residuals, think about how we can determine if we are in fact in line with these assumptions or not. What is Regression Analysis? Regression analysis is a set of statistical methods used for the estimation of relationships between a dependent variable and one or more independent variables. It can be utilized to assess the strength of the relationship between variables and for modeling the future relationship between them. Regression analysis includes several variations, such as linear, multiple linear, and nonlinear. The most common models are simple linear and multiple linear. Nonlinear regression analysis is commonly used for more complicated data sets in which the dependent and independent variables show a nonlinear relationship. 166 CU IDOL SELF LEARNING MATERIAL (SLM)

Regression analysis offers numerous applications in various disciplines, including finance. Regression Analysis – Linear Model Assumptions Linear regression analysis is based on six fundamental assumptions: 1. The dependent and independent variables show a linear relationship between the slope and the intercept. 2. The independent variable is not random. 3. The value of the residual (error) is zero. 4. The value of the residual (error) is constant across all observations. 5. The value of the residual (error) is not correlated across all observations. 6. The residual (error) values follow the normal distribution. Regression Analysis – Simple Linear Regression Simple linear regression is a model that assesses the relationship between a dependent variable and an independent variable. The simple linear model is expressed using the following equation: Y = a + bX + ϵ Where:  Y – Dependent variable  X – Independent (explanatory) variable  a – Intercept  b – Slope  ϵ – Residual (error) Regression Analysis – Multiple Linear Regression Multiple linear regression analysis is essentially similar to the simple linear model, with the exception that multiple independent variables are used in the model. The mathematical representation of multiple linear regression is: Y = a + bX1 + cX2 + dX3 + ϵ Where:  Y – Dependent variable  X1, X2, X3 – Independent (explanatory) variables  a – Intercept  b, c, d – Slopes  ϵ – Residual (error) 167 CU IDOL SELF LEARNING MATERIAL (SLM)

Multiple linear regressionsfollow the same conditions as the simple linear model. However, since there are several independent variables in multiple linear analyses, there is another mandatory condition for the model:  Non-collinearity: Independent variables should show a minimum correlation with each other. If the independent variables are highly correlated with each other, it will be difficult to assess the true relationships between the dependent and independent variables. Regression Analysis in Finance Regression analysis comes with several applications in finance. For example, the statistical method is fundamental to the Capital Asset Pricing Model (CAPM). Essentially, the CAPM equation is a model that determines the relationship between the expected return of an asset and the market risk premium. The analysis is also used to forecast the returns of securities, based on different factors, or to forecast the performance of a business. Learn more forecasting methods in CFI’s Budgeting and Forecasting Course! 11.5 PROCESS OF REGRESSION ANALYSIS Assumptions of regression Number of cases When doing regression, the cases-to-Independent Variables (IVs) ratio should ideally be 20:1; that is 20 cases for every IV in the model. The lowest your ratio should be is 5:1 (i.e., 5 cases for every IV in the model). Data Accuracy If you have entered the data (rather than using an established dataset), it is a good idea to check the accuracy of the data entry. If manager does not want to re-check each data point, you should at least check the both, minimum and maximum value for each variable to ensure that all values for each variable are \"valid.\" For example, a variable that is measured using from 1 to 5 scales should not have a value of 8. Missing data You also want to look for missing data. If specific variables have a lot of missing values, you may decide not to include those variables in your analyses. If only a few cases have any missing values, then you might want to delete those cases. If there are missing values for several cases on different variables, then you probably don't want to delete those cases (because a lot of your data will be lost). If there are not too much missing data, and there does not seem to be any pattern in terms of what is missing, then you don't really need to worry. Just run your regression, and any cases that do not have values for the variables used in that 168 CU IDOL SELF LEARNING MATERIAL (SLM)

regression will not be included. Although tempting, do not assume that there is no pattern; check for this. To do this, separate the dataset into two groups: those cases missing values for a certain variable, and those not missing a value for that variable. Using t-tests, you can determine if the two groups differ on other variables included in the sample. For example, you might find that the cases that are missing values for the \"salary\" variable are younger than those cases that have values for salary. You would want to do t-tests for each variable with a lot of missing values. If there is a systematic difference between the two groups (i.e., the group missing values vs. the group not missing values), then you would need to keep this in mind when interpreting your findings and not overgeneralize. After examining your data, you may decide that you want to replace the missing values with some other value. The easiest thing to use as the replacement value is the mean of this variable. Some statistics programs have an option within regression where you can replace the missing value with the mean. Alternatively, you may want to substitute a group mean (e.g., the mean for females) rather than the overall mean. The default option of statistics packages is to exclude cases that are missing values for any variable that is included in regression. (But that case could be included in another regression, as long as it was not missing values on any of the variables included in that analysis.) You can change this option so that your regression analysis does not exclude cases that are missing data for any variable included in the regression, but then you might have a different number of cases for each variable. Outliers You also need to check your data for outliers (i.e., an extreme value on a particular item) an outlier is often operationally defined as a value that is at least 3 standard deviations above or below the mean. If you feel that the cases that produced the outliers are not part of the same \"population\" as the other cases, then you might just want to delete those cases. Alternatively, you might want to count those extreme values as \"missing,\" but retain the case for other variables. Alternatively, you could retain the outlier, but reduce how extreme it is. Specifically, you might want to recode the value so that it is the highest (or lowest) non- outlier value. Normality You also want to check that your data is normally distributed. To do this, you can construct histograms and \"look\" at the data to see its distribution. Often the histogram will include a line that depicts what the shape would look like if the distribution were truly normal (and you can \"eyeball\" how much the actual distribution deviates from this line). This histogram shows that age is normally distributed: 169 CU IDOL SELF LEARNING MATERIAL (SLM)

Fig. 11.1 How does regression analysis work? In order to conduct a regression analysis, you’ll need to define a dependent variable that you hypothesize is being influenced by one or several independent variables. You’ll then need to establish a comprehensive dataset to work with. Administering surveys to your audiences of interest is a terrific way to establish this dataset. Your survey should include questions addressing all of the independent variables that you are interested in. Let’s continue using our application training example. In this case, we’d want to measure the historical levels of satisfaction with the events from the past three years or so (or however long you deem statistically significant), as well as any information possible in regards to the independent variables. Perhaps we’re particularly curious about how the price of a ticket to the event has impacted levels of satisfaction. To begin investigating whether or not there is a relationship between these two variables, we would begin by plotting these data points on a chart, which would look like the following theoretical example. 170 CU IDOL SELF LEARNING MATERIAL (SLM)

11.6 INTRODUCTION OF MARKET BASKET ANALYTICS Market basket analysis is a data mining technique used by retailers to increase sales by better understanding customer purchasing patterns. It involves analyzing large data sets, such as purchase history, to reveal product groupings, as well as products that are likely to be purchased together. What Is Market Basket Analysis? Market Basket Analysis is a technique which identifies the strength of association between pairs of products purchased together and identifies patterns of co-occurrence. A co- occurrence is when two or more things take place together. Market Basket Analysis creates If-Then scenario rules, for example, if item A is purchased then item B is likely to be purchased. The rules are probabilistic in nature or, in other words, they are derived from the frequencies of co-occurrence in the observations. Frequency is the proportion of baskets that contain the items of interest. The rules can be used in pricing strategies, product placement, and various types of cross-selling strategies. 11.7 APPLICATION OF MARKET BASKET ANALYTICS How Market Basket Analysis Works In order to make it easier to understand, think of Market Basket Analysis in terms of shopping at a supermarket. Market Basket Analysis takes data at transaction level, which lists all items bought by a customer in a single purchase. The technique determines relationships of what products were purchased with which other product(s). These relationships are then used to build profiles containing If-Then rules of the items purchased. Practical Applications of Market Basket Analysis When one hears Market Basket Analysis, one thinks of shopping carts and supermarket shoppers. It is important to realize that there are many other areas in which Market Basket Analysis can be applied. An example of Market Basket Analysis for a majority of Internet users is a list of potentially interesting products for Amazon. Amazon informs the customer that people who bought the item being purchased by them, also reviewed or bought another list of items. A list of applications of Market Basket Analysis in various industries is listed below:  Retail. In Retail, Market Basket Analysis can help determine what items are purchased together, purchased sequentially, and purchased by season. This can assist retailers to determine product placement and promotion optimization (for instance, combining product incentives). Does it make sense to sell soda and chips or soda and crackers? 171 CU IDOL SELF LEARNING MATERIAL (SLM)

 Telecommunications. In Telecommunications, where high churn rates continue to be a growing concern, Market Basket Analysis can be used to determine what services are being utilized and what packages customers are purchasing. They can use that knowledge to direct marketing efforts at customers who are more likely to follow the same path. For instance, Telecommunications these days is also offering TV and Internet. Creating bundles for purchases can be determined from an analysis of what customers purchase, thereby giving the company an idea of how to price the bundles. This analysis might also lead to determining the capacity requirements.  Banks. In Financial (banking for instance), Market Basket Analysis can be used to analyze credit card purchases of customers to build profiles for fraud detection purposes and cross-selling opportunities.  Insurance. In Insurance, Market Basket Analysis can be used to build profiles to detect medical insurance claim fraud. By building profiles of claims, you are able to then use the profiles to determine if more than 1 claim belongs to a particular claimee within a specified period of time.  Medical. In Healthcare or Medical, Market Basket Analysis can be used for comorbid conditions and symptom analysis, with which a profile of illness can be better identified. It can also be used to reveal biologically relevant associations between different genes or between environmental effects and gene expression. Data Requirement 1. Baskets  This column identifies the individual baskets.  Values can be categoric or numeric to identify the baskets. 2. Products  This column has all the items that are included in each basket.  Values of items can be categoric or numeric. For example, from the table 1 below: 172 CU IDOL SELF LEARNING MATERIAL (SLM)

Procedure: How to Create an Association Model Using Market Basket Analysis In this example, we are going to create a model for Market Basket Analysis of purchases at a grocery store. We will use the Basket data set that contains observations on the purchases of particular items, such as milk, cheese, and apples. Define the Model Data.  Load the Baskets data set into RStat. For more information on loading data into RStat, see Getting Started with RStat.  Turn off sampling by unchecking the Partition check box.  For the Target Data Type, leave the Auto radio button selected.  Select BASKET as the Ident variable, which defines the basket.  Select PRODUCT as the Target variable, which defines the products in the basket.  Click Execute to run the Model Data. Types of market basket analysis There are two types of market basket analysis: 1. Predictive market basket analysis: This type considers items purchased in sequence to determine cross-sell 2. Differential market basket analysis: This type considers data across different stores, as well as purchases from different customer groups during different times of the day, month or year. If a rule holds in one dimension (like store, time period or customer group), but does not hold in the others, analysts can determine the factors responsible for the exception. These insights can lead to new product offers that drive higher sales. 173 CU IDOL SELF LEARNING MATERIAL (SLM)

11.8 SUMMARY Regression analysis is a Statistical Forecasting model that is concerned with describing and evaluating the relationship between a given variable (usually called the dependent variable) and one or more other variables (usually known as the independent variables. The six “steps” to interpreting the result of a regression analysis are: 1. Look at the prediction equation to see an estimate of the relationship. 2. Refer to the standard error of the prediction (in the appropriate model) when making predictions for individuals, and the standard error of the estimated mean when estimating the average value of the dependent variable across a large pool of similar individuals. 3. Refer to the standard errors of the coefficients (in the most complete model) to see how much you can trust the estimates of the effects of the explanatory variables. 4. Look at the significance levels of the t-ratios to see how strong is the evidence in support of including each of the explanatory variables in the model. 5. Use the “adjectived” coefficient of determination to measure the potential explanatory power of the model. 6. Compare the beta-weights of the explanatory variables in order to rank them in order of explanatory importance. Market basket analysis is a data mining technique used by retailers to increase sales by better understanding customer purchasing patterns. It involves analyzing large data sets, such as purchase history, to reveal product groupings, as well as products that are likely to be purchased together. In the retail industry, market basket analysis explores the relationship between products by considering the co-occurrence of purchases in previous transactions. Association analysis is a generalization of applications, like market basket analysis, and is now commonly applied in clickstream analysis, cross-selling recommendation engines, and information security. Association analysis is an unsupervised data science technique where there is no target variable to predict. Instead, the algorithm reviews each transaction containing a number of items (products) and extracts useful relationship patterns among the items in the form of rules. The challenge in association analysis is to differentiate a significant observation against unscrupulous rules. The Apriori and Frequent Pattern Growth algorithms offer efficient approaches to extract these rules from large datasets in the transaction logs. 11.9 KEYWORDS  Regression analysis is a common technique in market research which helps the analyst understands the relationship of independent variables to a dependent variable. 174 CU IDOL SELF LEARNING MATERIAL (SLM)

 Regression has a huge range of real-life business & marketing applications.  Ordinary least squares (OLS) regression. - An OLS model operates by fitting a linear line through the data that minimizes the squared sum of the residuals.  Multiple Linear Regressions:-Multiple linear regression analysis is essentially similar to the simple linear model, with the exception that multiple independent variables are used in the model.  Market Basket Analysis:-Market Basket Analysis is a technique which identifies the strength of association between pairs of products purchased together and identify patterns of co-occurrence 11.10 LEARNING ACTIVITY 1. Define the concept of Regression Analysis ___________________________________________________________________________ _____________________________________________________________________ 2. What the scope of Regression Analysis in Marketing? ___________________________________________________________________________ _____________________________________________________________________ 3. Define the concept of Market Basket Analytics? ___________________________________________________________________________ _______________________________________________________________ 11.11 UNIT END QUESTIONS A. Descriptive Questions Short Questions 1. What is Regression Analysis? 2. How to develop Regression Analysis Methods? 3. Explain the scope of Regression Analysis. 4. Explain different Types of Regression Analysis 5. Identify the scope of Regression Analysis 6. Define the concept of Market Basket Analysis. 7. Explain the importance of Market Basket Analytics 8. Explain the different steps of Market Basket Analytics? Long Questions 175 CU IDOL SELF LEARNING MATERIAL (SLM)

1. What is scope of Regression Analysis? 176 2. Explain different types of Regression Analysis. 3. Explain the purpose of Regression Analysis 4. What is Process of Regression Analysis? 5. What the factors to be considered for Regression Analysis? 6. What is Market Basket Analysis? 7. Suggest a suitable Analysis Model for D’Mart 8. What is the scope of Market Basket Analytics? B. Multiple choice Questions 1. Regression Model is applicable for ___________ a. Product b. Advertising c. Free Sample d. Business Prediction 2. Good Regression Analysis is used by ___________ a. Food Malls b. Chemists c. Wholesaler d. Direct Marketing 3. Regression Analysis is widely followed by _________ a. India b. Middle East c. Bangladesh d. Advanced Counties 4. ____________ is considered for setting Regression Analysis a. Demand & Supply Factor b. Weekly sales Data CU IDOL SELF LEARNING MATERIAL (SLM)

c. Target Market d. Sales Quota 5. The main purpose of Market Basket Analysis _____________ & ____________ a. Smooth delivery & JIT delivery to end customers b. Market feedback & Data collection c. Maintain Inventory & manage stock keeping Units d. Customer satisfaction & goodwill Answers 1-d, 2-a, 3-d, 4-b, 5-c. 11.12 REFERENCES Textbooks  T1 Grigsby, M. 2115. Marketing Analytics: A practical guide to real marketing science, Its Ed., Kogan Page, India, ISBN: 978-0749474171.  T2 Winston, W. 2114.Marketing Analytics: Data Driven Technique using MS. Excel. Ist Ed. John Wiley & Sons, India, ISBN: 978-1118373439. Reference Books:  R1 Grigsby, M. 2116. Advanced Customer Analytics: Targeting, Valuing, Segmenting and Loyalty Techniques (Marketing Science). Ist Ed. Kogan Page. India. ISBN: 978-0749477158. Websites  https://springer.com  https://michaelpawlicki.com  https://statisticshowto.com  https://stattrek.com  https://slideshare.com 177 CU IDOL SELF LEARNING MATERIAL (SLM)

UNIT 12: WEB ANALTYTICS, SENTIMENT ANALYSIS STRUCTURE 12.0 Learning Objectives 12.1 Introduction of Web Analytics 12.2 Concepts of Web Analytics 12.3 Importance of Web Analytics 12.4 Process of Web Analytics 12.5 Concept of Sentiment Analysis 12.6 Types of Sentiment Analysis 12.7 Summary 12.8 Keywords 12.9 Learning Activity 12.10 Unit End Questions 12.11 References 12.0 LEARNING OBJECTIVES After studying this course you will obtain knowledge of Web Analytics? Contemporary Website analytics is the science of various analyses with modern approach that focuses on the World Wide Web. Web Analytics focuses on optimizing an organization's digital ecosystem by collecting, analysing and enabling the making of data-informed decisions. You will learn about five basic web analytics metrics and then to review them in a better way.  Bounce Rate. Bounce rate is one of the famous metrics in Google Analytics. ...  Exit Rate. ...  Conversion Rate. ...  Average Time on Page. ...  Average Time on Site. 12.1 INTRODUCTION OF WEB ANALYTICS Web Analytics or Online Analytics refers to the analysis of quantifiable and measurable data of your website with the aim of understanding and optimizing the web usage. CU IDOL SELF LEARNING MATERIAL (SLM)

Web analytics studies of various business issues. For example, histories of visitor data, and sales data, actual conversion date etc. Web analytics is the collection, reporting, and analysis of website data. The objective is on identifying results based on your marketing goals and using the website data to determine the review by success or failure of those goals and to drive or modify strategy and improve the user's experience. 12.2 CONCEPTS OF WEB ANALYTICS Web analytics is the process of analyzing number of visits & the behavior of visitors to a website. This involves review of tracking, reviewing and reporting various data to measure web activity, including the use of a website and its useful components, such as webpages, images and videos. Data collected through web analytics may include traffic sources, with referring sites, various page views, paths taken and conversion rates. The detailed compiled data often forms a part of customer relationship management analytics (CRM & CEM analytics) to facilitate and helps to improve business growth with better&sound, logical business decisions. What all can you Analyze through Web Analytics? With the support of Web analytics, you can analyze the following:  Potential Audience  Web traffic Sources  Average or total of visits and visitors  The top ranking pages  Goals converted  Bounce and exit rates  Web issues if any 12.3 IMPORTANCE OF WEB ANALYTICS What are web analytics? Web analytics is the process of analyzing the behavior of visitors to a website. This involves tracking, reviewing and reporting data to measure web activity, including the use of a website and its components, such as webpages, images and videos. Data collected through web analytics may include traffic sources, referring sites, page views, paths taken and conversion rates. The compiled data often forms a part of customer relationship management analytics (CRM analytics) to facilitate and streamline better business decisions. 179 CU IDOL SELF LEARNING MATERIAL (SLM)

Web analytics helps to the business to retain, maintain its customers, attract more visitors and increase the sales volume of each customer spends. Analytics will help in the following ways:  Determine the likelihood that a given customer will repurchase a product after purchasing it in the past.  Personalize the site to customers who visit it repeatedly.  Track & Monitor the amount of money individual customers or specific groups of customers spend.  Observe the geographic regions from which the most and the least customers visit the site and purchase specific products.  Visualize which brands, goods & products potentials customers can buy are most and likely to buy in the future. The objective of web analytics is to serve as a business metric for promoting specific brands of products to the customers who are most likely to buy them and to determine which products a specific customer is most likely to buy 6 Reasons Why Website Analytics are useful for Your Business Growth  Updated on Your Visitors Well and Enhance User Experience. ...  Know you’rebestcontent and Focus on it....  It Helps Your Site's SEO. ...  Track Top Referrals and Build Strategies to Gain More of Them. ...  Utilize Your Top Outbound Links as Partnership Opportunities. Website analytics highlights you with the actual reports , information and analytics on how your site visitors behave once on your website; who they are by their profile, place, status, income , family , life style , age, gender, location, etc.; how they landed on your site (traffic source); the most popular content on your site; your total conversions; and so on. With this information in hand, you can plan fully informed business strategies and grow your business faster. 12.4 PROCESS OF WEB ANALYTICS Five key web analytics you should be tracking 1. Overall traffic. When we talk about web traffic, we refer to the number of visits your site gets over a particular & specific period of time. ... 2. Bounce rate. ... 3. Traffic sources. ... 4. Desktop vs. ... 180 CU IDOL SELF LEARNING MATERIAL (SLM)

5. New and returning visitors. Get to Know Your Visitors Well and Enhance User Experience In day today business when it comes to making an any kins of (big or small) business decisions, it’s important to ensure your decision doesn’t affect your existing customers, but rather enhances their user experience. It’s more useful with rewarding if it can attract & acquire more new users. So, to make a safe, sound and informed decision, a manager needs to know your visitors first. When you know who your site visitors are by their age, gender, geographic location, interest topics, etc., you can take proper measures to enhance their user experience. Similarly, when you study &refer the technology (device, operating system, and browsers) they’re using to browse your site, you can test your site’s compatibility with those modern technologies and make necessary modifications & improvements. For example, let’s consider how the popular website analytics tool Monster Insights helps you improve your site’s overall user experience.  Device breakdown: If a large section of your visitors is using mobile device, it’s a clear message that will help for making your site mobile-friendly.  Language and Place & location: You will review where most of your users are located and create translations for your site if it’s required.  Age and Interest Categories: When you identify the actual age and interest group as your larger section of audience, you can customize your site by making it more useful to them. With these improvements, you can make your site audience stay longer and ultimately turn them into customers. 2. Know you’rebestcontent and Focus on It Website analytics tools like Google Analytics and Monster Insights show you exactly which content gets the most visits, average duration, and bounce rate for the individual pages, so you can analyze, and optimize, for better engagement. You can add more call to action (CTA) buttons, purchase links, etc. on the top pages of your site and boost your conversions. Additionally, you can view & update the top most landing pages with the latest information or revamp their whole design and structure to make them look new, fresh and updated. Again to that, you will know what type of content really works and what doesn’t. That way, you can alter with the type of content getting more visits to view boost your site engagement and gain more potential customers. 181 CU IDOL SELF LEARNING MATERIAL (SLM)

3. It useful for Your Site’s SEO Search engine optimization (SEO) is one of the most crucial & important aspects in determining your business growth. The more organic traffic your business site receives, the more leads, referrals and conversions it gains. Website analytics help your site’s SEO in various ways. By reviewing your visitors’ demographics and interests, you can develop targeted content and get better visibility on search engines. Furthermore, you can gain some more insights on backlinks by tracking your referrals. Moreover, using Monster Insights and Google Analytics, you can connect & attach your Analytics account with Google Search Console and track what search queries are sending you the most traffic. It provides you with the actual input data of total clicks, impressions, average click-through rate (CTR), and average position. Fig. 12.1 You can also set up site search tracking and track what your visitors are looking for on your site. 4. Track Top Referrals and Build Strategies to Gain More of Them Using website analytics, you can track who referred most traffic to your business site, analyze, and focus on strategies to gain more referrals from them. For example, if your site receives most traffic from search engines, it means your site SEO is strong. Now with little extra effort, you can improve your website’s online visibility and gain more traffic than ever before. 5. Utilize Your Top Outbound Links as Partnership Opportunities Website analytics not only give your insight into your site referrals but also whom you are referring to or the outbound links. Using Google Analytics or Monster Insights, you can view 182 CU IDOL SELF LEARNING MATERIAL (SLM)

the top links clicked on your website that go to other websites, analyze, and reach out to those websites with partnership offers. You can see many businesses grow out of collaborations with other related businesses through mutual recommendations and cross-promotions. Looking for the right business partner, reaching out, and asking for partnership can’t be easy until you have a clue regarding exactly what works for the partnership. So, using Google Analytics outbound links reports, you show can show other business owners exactly what works between the two businesses and easily persuade them into partnerships. 6. Easily Track Your Ecommerce Metrics and Utilize Them for More Sales Whether you are selling physical products, software, or online services, the sales report is the most important report you should get to know. Thankfully, website analytics tools like Google Analytics and Monster Insights show you all your important ecommerce metrics like total revenue, conversion rates, top products, top referral sources, etc. in a single report. Then, with the exact idea of who is referring you most sales, you can create strategies to gain even more. Setting up ecommerce tracking is very easy for Word Press sites using Monster Insights. With just a few clicks, you can enable this option and view your most important ecommerce data. Which Website Analytics Tool Should You Use? Now that you know the importance of website analytics, you might be wondering “which is the best website analytics tool?” Google Analytics is by far the most popular analytics tool available, and it’s 100% free. The problem is that it has a steep learning curve. If you’re not tech savvy and cannot code, then it would be very challenging for you to set up advanced tracking. That’s why we created Monster Insights. It’s the most user-friendly Google analytics Word Press plugin and it simplifies the entire process of setting up Google Analytics and tracking important website analytics for Word Press sites. This article is a step-by-step guide to creating a web analytics measurement strategy and plan. 1. Step One: Document Business Objectives. 2. Step Two: Create Goals / Strategies. 3. Step Three: Choose Key Performance Indicators (KPIs) 4. Step Four: Set Targets/Benchmarks. 5. Step Five: Determine Reporting and Segments. 183 CU IDOL SELF LEARNING MATERIAL (SLM)

12.5 CONCEPTS OF SENTIMENT ANALYSIS Sentiment Analysis is the systematic process of determining whether a piece of writing is positive, negative or neutral. ... Sentiment analysis helps with data analysts within large enterprises to know & understand public opinion, conduct deep & desired market research, monitor brand image , image and product reputation, and understand customer experiences with CEM Customer Expectation Management Sentiment analysis is contextual mining of text which identifies and extracts subjective information in source material, and helping a business to understand the social sentiment of their brand, product or service while monitoring online conversations. With the recent contemporary techniques with advances in deep learning, the ability of algorithms to analyze text has improved a lot with great impact. Proper & Creative use of advanced artificial intelligence techniques can be an effective tool for doing in-depth marketing research. We believe it is important to classify incoming customer conversation about a brand based on following lines: 1. Main aspects of a brand’s product and service that customers care about. 2. Customer’s intentions and reactions concerning those aspects. 12.6 TYPES OF SENTIMENT ANALYSIS 3 Benefits of Using a Marketing Dashboard  Faster, More Scalable Reporting. Regular reporting on marketing performance is a fact of business & channels, especially for many agencies. ...  Advanced Insight. With that you have to stop with your monthly dashboard. ...  Increased Accountability = Increased Revenue, Retention and Budget. Faster, More Scalable Reporting Regular reporting on marketing performance is a business activity, especially for many agencies. You have to show clients or internal stakeholders how their investment in your services is performing. Dashboards are a more visually appealing way to mass communication that information to clients than a spreadsheet or a PowerPoint, which usually aren’t interactive or nearly as flexible as a dashboard is. And once the dashboard is active & and running, it will automatically update with new data as it becomes available — something a PowerPoint can’t do. You don’t have to spend the last few days of each month racing to build reports. And it puts more power in your end-user’s hands to make up-to-the-minute decisions about advertising budgets. 184 CU IDOL SELF LEARNING MATERIAL (SLM)

Dashboards are also more scalable. Once you have constructed your basic dashboard, you can quickly duplicate it and, with a few adjustments, use it for other audiences. This is an especially useful point for advertising agencies with dozens or hundreds of clients. Or for franchises that handle marketing and media for large networks of franchisees. Advanced Insight Not that you have to stop with your monthly dashboard. You can also create more advanced dashboards that are designed to solve specific business problems. Case in point: Maybe you want to build a dashboard with a built-in calculator for determining where, when and how much to spend on advertising. That calculator — drawing on your historical performance data — will help with you a better idea of what results you spend will create, on the basis of what occurred in previous years. Increased Accountability = Increased Revenue, Retention and Budget For well reputed brands, a good dashboard will demonstrate the positive image &value of marketing and make it useful to make the case for next year’s budget. It could also give your marketing team a louder voice in your organization’s overall business strategy, if your insights lead the marketing unit to develop new products or pursue new audiences. For agencies, your dashboard will do a better job of showcasing the ROI you’re creating for clients or stakeholders. That will benefit with a stronger argument for retaining those clients. And you absolutely can (and should) charge for more sophisticated dashboards. 12.7 SUMMARY Web Analytics with its Best Practices Web analytics can strongly support the qualitative research and testing finding. Some best practices to record & review related to this field are:  Encourage a data-driven environment for decision making. After collecting the relevant data & information to answer whether you have achieved (or fail to meet) your goals, find out what you can be done to improve your KPIs. Is there high-value content (on the basis of user feedback to the website) that is not getting any traffic? Find out why through user path analysis or engagement analysis of top sources for that page. Leverage the experimentation & testing tools to find out different solutions and find the best placement that generates the most engagement for that page.  Avoid only providing traffic reports. Reporting about regular visits, page views, top sources, or top pages only skims the surface. A Large numbers can be misleading; just because there is more traffic or time spent on site doesn’t mean that there is success. Reporting these numbers is largely tactical; after all, what do 7 million visits have to do with the success of your program? 185 CU IDOL SELF LEARNING MATERIAL (SLM)

 Always provide insights with the data. Reporting metrics to your stakeholders with no insights or tie-ins to your business or user goals misses the main point. Make sure that the data relevant and meaningful by demonstrating how the website data shows areas of success and of improvement on your site.  Avoid being snapshot-focused in reporting. Focusing on visits or looking only within a specific time period doesn’t capture the richer and more complex web experiences that are happening online now  Communicate clearly with stakeholders. Ensure constant consistency in the information you provide, know your target audience, and know the strength & weaknesses of your system and disclose them to your stakeholders. 12.8 KEYWORDS  Web Analytics Basics:Web analytics is the collection, reporting, and analysis of website data.  CTR: - Click Through Rate  SEO: - Search Engine Optimizations  E-Commerce: - electronic commerce, online shopping  Sentiment Analysis: - is the systematic process of determining whether a piece of writing is positive, negative or neutral. 12.9 LEARNING ACTIVITY 1. What are Web Analytics? ___________________________________________________________________________ _____________________________________________________________________ 2. What is the purpose of web analytics in Modern Marketing? ___________________________________________________________________________ _____________________________________________________________________ 3. Define the concept of Sentiment Analysis? ___________________________________________________________________________ _______________________________________________________________ 12.10 UNIT END QUESTIONS A. Descriptive Questions 186 Short Questions 1. Define Web Analytics 2. What is purpose of Web Analytics? CU IDOL SELF LEARNING MATERIAL (SLM)

3. Explain the objectives of Web Analytics? 187 4. Define the concept of Sentiment Analysis 5. Explain importance of Sentiment Analysis in Marketing Long Questions 1. What is importance of Web Analytics? 2. Define the process of Web Analytics 3. How Does Web Analytics work? 4. What data & reports you analyse through Web Analytics? 5. What is the scope of Sentiment Analysis? 6. Explain the different types of Sentiment Analysis? 7. Define the steps in Sentiment Analysis? 8. Why Sentiment Analysis is useful forbusiness? 9. Explain the common challenges in Sentiment Analysis. B. Multiple choice Questions 1. Web Analytics is part of ________ a. Product b. Customer Data Analysis c. Customer Meet d. Test Marketing 2. Web analytics is very useful in ___________ a. Google Analytics b. Market Survey c. Customer & Data Analysis d. Marketing Analytics 3. Important elements of web analytics are _________& ____________ a. Each Lead & Website visit b. Direct Sales Report & Sales Forecast c. Marketing Feedback & Customer Response CU IDOL SELF LEARNING MATERIAL (SLM)

d. Exit Rate & Bounce Rate 4. Sentiment Analysis is useful for ________ a. Sales Analysis b. Digital Marketing c. Consumer Behaviours d. Product Development 5. The Sentiment Analysis has a vital impact on _____________ a. Customer Purchases b. Customer & Competition c. Distribution d. Sales Reports Answers 1-b, 2-d, 3-d, 4-c, 5-a. 12.11 REFERENCES Textbooks  T1 Grigsby, M. 2115. Marketing Analytics: A practical guide to real marketing science, Its Ed., Kogan Page, India, ISBN: 978-0749474171.  T2 Winston, W. 2114.Marketing Analytics: Data Driven Technique using MS. Excel. Ist Ed. John Wiley & Sons, India, ISBN: 978-1118373439. Reference Books:  R1 Grigsby, M. 2116. Advanced Customer Analytics: Targeting, Valuing, Segmenting and Loyalty Techniques (Marketing Science). Ist Ed. Kogan Page. India. ISBN: 978-0749477158. Websites  https://springer.com  https://michaelpawlicki.com  https://statisticshowto.com 188 CU IDOL SELF LEARNING MATERIAL (SLM)

 https://stattrek.com  https://slideshare.com 189 CU IDOL SELF LEARNING MATERIAL (SLM)

UNIT 13: CLUSTER ANALYSIS, CONJOINT ANALYSIS STRUCTURE 13.0 Learning Objectives 13.1 Introduction of Cluster Analysis 13.2 Objectives of Cluster Analysis 13.3 Importance of Cluster Analytics 13.4 Working of Cluster Analysis 13.5 Characteristics of Conjoint Analysis 13.6 Methods of Conjoint Analysis 13.7 Importance of Conjoint Analysis 13.8 Summary 13.9 Keywords 13.10 Learning Activity 13.11 Unit End Questions 13.12 References 13.0 LEARNING OBJECTIVES After studying this unit, you will be able to  The objective of clustering is to find out distinct groups in a dataset.  Assessment and pruning of hierarchical model-based clustering.  The aim of clustering is to identify distinct groups in a dataset. 13.1 INTRODUCTION OF CLUSTER ANALYSIS 190 CU IDOL SELF LEARNING MATERIAL (SLM)

Fig. 13.1 Cluster analysis or clustering is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). ... Clustering can therefore be formulated as a multi-objective optimization problem. Cluster analysis is an exploratory analysis that tries to identify structures within the data. Cluster analysis is also called segmentation analysis or taxonomy analysis. More specifically, it tries to identify homogenous groups of cases if the grouping is not previously known. The main objective of cluster analysis is to discover natural grouping of a set of patterns, points or objects.\" Clustering can be defined on the basis of similarity, such that the intraclass variation is low while the interclass variation is high. Clusters differ in terms of shape, size and density. Clustering is a type of unsupervised learning method of machine learning. ... In other words, the clusters are regions where the density of similar data points is high. In Business it is used for the analysis of the input & data set, to find insightful data among huge data sets and draw correct & relevant inferences from it. The clustering has been defined as below, 1. Definition Clustering refers to dividing a data set into different classes or clusters are set of a certain standard (such as distance criteria), for getting the required so that the similarity of data objects in the same cluster is as close as possible the difference between data objects that are uncommon cluster is as large as possible. That is, after clustering, the same type of data is gathered together as close as and different data are separated as much as possible. Cluster analysis or clustering is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). ... Cluster analysis itself is not one specific algorithm, but the general task to be solved. 191 CU IDOL SELF LEARNING MATERIAL (SLM)

13.2 OBJECTIVES OF CLUSTER ANALYSIS Cluster analysis is a group of multivariate techniques whose primary purpose is to group objects (e.g., respondents, products, or other entities) based on the characteristics they possess. It is a means of grouping records based upon attributes that make them similar. If plotted geometrically, the objects within the clusters will be close together, while the distance between clusters will be farther apart. The goal of clustering is to reduce the amount of data by categorizing or grouping similar data items together. Objective of clustering • Discover structures and patterns in high-dimensional data. • Group data with similar patterns together. • This reduces the complexity and facilitates interpretation 13.3 IMPORTANCE OF CLUSTER ANALYSIS T is normally used for exploratory data analysis and as a method of discovery by solving classification issues. In the business application and decision-making context, cluster analysis can be a key process to know the distinguishable attributes of a large population. Cluster analysis has long played an important role in a broad variety of areas, such as psychology, biology, computer sciences. It has established as a precious tool for marketing and business areas, thanks to its capability to help in decision-making processes. Traditionally, clustering approaches concentrate on purely numerical or categorical data only. An important area of cluster analysis deals with mixed data, composed by both numerical and categorical attributes. Clustering mixed data is not simple, because there is a strong gap between the similarity metrics for these two kinds of data. In this review we provide some technical details about the kind of distances that could be used with mixed-data types. Finally, we emphasize as in most applications of cluster analysis practitioners focus either on numeric or categorical variables, lessening the effectiveness of the method as a tool of decision-making. Cluster analysis is a statistical technique that sorts observations into similar sets or groups. The use of cluster analysis presents a complex challenge because it requires several methodological choices that determine the quality of a cluster solution. This paper chronicles the application of cluster analysis in strategic management research, where the technique has been used since the late 1970s to investigate issues of central importance. Analysis of 45 published strategy studies reveals that the implementation of cluster analysis has been often less than ideal, perhaps detracting from the ability of studies to generate knowledge. Given these findings, suggestions are offered for improving the application of cluster analysis in future inquiry. 192 CU IDOL SELF LEARNING MATERIAL (SLM)

Cluster Analysis and Its Significance to Business A statistical tool, cluster analysis is used to classify objects into groups where objects in one group are more similar to each other and different from objects in other groups. It is normally used for exploratory data analysis and as a method of discovery by solving classification issues. In the business application and decision-making context, cluster analysis can be a key process to know the distinguishable attributes of a large population. Cluster analysis methods help segregate the population into different marketing buckets or groups based on the campaign objective, which can be highly effective for targeted marketing initiatives. This can save a lot of time, effort, and money spent hitting the dart in the dark and empowers the leadership team to focus on either run separate initiatives for each group of audience or focus on just one. Applications of Cluster Analysis There are many applications for cluster analysis across various domains. Some of the popular applications include the following:  Market segmentation  Social network analysis  Recommendation engines  Anomaly detection  Medical imaging  Image segmentation Learning means that given some training data set, we want to predict the class labels of the testing data set. Secondly if you look from supervised learning in which class labels are known and unsupervised learning in which class labels are unknown, there is a third type of hybrid learning called semi-supervised. In this type of learning, we have class labels for some portion of the training set. But instead of discarding the large portion of training set with unlabelled data, it is also used in the learning process. In place of using class labels, pair-wise constraints are used. According to the some suggested must-link constraint two objects should be assigned to the same cluster while cannot-link constraint specifies that the cluster labels of two objects should be different. Cluster analysis or clustering is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). It is a main purpose of exploratory data analysis, and a simple technique for statistical data analysis, used in many fields, including pattern recognition, image analysis, information retrieval, bioinformatics, data compression, Digital graphics and machine learning 193 CU IDOL SELF LEARNING MATERIAL (SLM)

13.4 WORKING OF CLUSTER ANALYSIS Cluster analysis or clustering is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). It is a main task of exploratory data analysis, and a common technique for statistical data analysis, used in many fields, including pattern recognition, image analysis, information retrieval, bioinformatics, data compression, computer graphics and machine learning. Cluster analysis itself is not one specific algorithm, but the general task to be solved. It can be achieved by various algorithms that differ significantly in their understanding of what constitutes a cluster and how to efficiently find them. Popular notions of clusters include groups with small distances between cluster members, dense areas of the data space, intervals or particular statistical distributions. Clustering can therefore be formulated as a multi- objective optimization problem. The appropriate clustering algorithm and parameter settings (including parameters such as the distance function to use, a density threshold or the number of expected clusters) depend on the individual data set and intended use of the results. Cluster analysis as such is not an automatic task, but an iterative process of knowledge discovery or interactive multi-objective optimization that involves trial and failure. It is often necessary to modify data preprocessing and model parameters until the result achieves the desired properties. The Benefits of Cluster Analysis Clustering allows researchers to identify and define patterns between data elements. Revealing these patterns between data points helps to distinguish and outline structures which might not have been apparent before, but which give significant meaning to the data once they are discovered. Once a clearly defined structure emerges from the dataset at hand, informed decision-making becomes much easier. The Different Types of Cluster Analysis There are three primary methods used to perform cluster analysis: Hierarchical Cluster This is the most common method of clustering. It creates a series of models with cluster solutions from 1 (all cases in one cluster) to n (each case is an individual cluster). This approach also works with variables instead of cases. Hierarchical clustering can group variables together in a manner similar to factor analysis. Finally, hierarchical cluster analysis can handle nominal, ordinal, and scale data. But, remember not to mix different levels of measurement into your study. 194 CU IDOL SELF LEARNING MATERIAL (SLM)

K-Means Cluster This method is used to quickly cluster large datasets. Here, researchers define the number of clusters prior to performing the actual study. This approach is useful when testing different models with a different assumed number of clusters. Two-Step Cluster This method uses a cluster algorithm to identify groupings by performing pre-clustering first, and then performing hierarchical methods. Two-step clustering is best for handling larger datasets that would otherwise take too long a time to calculate with strictly hierarchical methods. Essentially, two-step cluster analysis is a combination of hierarchical and k-means cluster analysis. It can handle both scale and ordinal data, and it automatically selects the number of clusters. What Does The Clustering Process Look Like? Step #1: Build and Distribute a Survey Your survey should be designed to include multiple measures of propensity to purchase and the preferences for the product at hand. It should be distributed to your population of interest, and your sample size should be large enough to inform statistically-based decisions. Step #2: Analyze Response Data It’s considered best practice to perform a factor analysis on your survey to minimize the factors being clustered. If after your factor analysis it’s concluded that a handful of questions are measuring the same thing, you should combine these questions prior to performing your cluster analysis. After reducing your data by factoring, perform the cluster analysis and decide how many clusters seem appropriate, and record those cluster assignments. You’ll now be able to view the means of all of your factors across clusters. Step #3: Take Informed Action! Comb through your data to identify differences in the means of factors, and name your clusters based on these differences. These differences between clusters are then able to inform your marketing, allowing you to target precise groups of customers with the right message, at the right time, in the right manner. In the first approach, they start with classifying all data points into separate clusters & then aggregating them as the distance decreases. In the second approach, all data points are classified as a single cluster and then partitioned as the distance increases. Also, the choice of distance function is subjective.  Increased performance: Multiple machines provide greater processing power. 195 CU IDOL SELF LEARNING MATERIAL (SLM)

 Simplified management: Clustering simplifies the management of large or rapidly growing systems. 13.5 CHARACTERISTICS OF CONJOINT ANALYSIS Two-Attribute Tradeoff Analysis Perhaps the earliest conjoint data collection method involved presented a series of attribute- by-attribute (two attributes at a time) tradeoff tables where respondents ranked their preferences for the different combinations of the attribute levels. For example, if two attributes each had three levels, the table would have nine cells and the respondents would rank their tradeoff preferences from 1 to 9. The two-factor-at-a-time approach makes few cognitive demands of the respondent and is simple to follow but it is both time-consuming and tedious. Moreover, respondents often lose their place in the table or develop some stylised pattern just to get the job done. Most importantly, however, the task is unrealistic in that real alternatives do not present themselves for evaluation two attributes at a time. Full-Profile Conjoint Analysis Full-profile conjoint analysis takes the approach of displaying a large number of full product descriptions to the respondent. The evaluation of these packages yields large amounts of information for each customer/respondent. Full-profile conjoint analysis has been a popular approach to measure attribute utilities. In the full-profile conjoint task, different product descriptions (or even different actual products) are developed and presented to the respondent for acceptability or preference evaluations. Each product profile represents a part of a fractional factorial experimental design that evenly matches the occurrence of each attribute with all other attributes. By controlling the attribute pairings, the researcher can correlate attributes with profile preferences and estimate the respondent’s utility for each level of each attribute tested. In the rating task, the respondent gives their preference or likelihood of purchase. While many features and levels may be studied, this type of conjoint is best used where a moderate number of profiles are presented, thereby minimising respondent fatigue. The advanced functionality of Qualtrics employs experimental designs to reduce the number of evaluation requests within the survey. The output and analysis accumulated from full-profile conjoint surveys is similar to that of other conjoint models. What Is Conjoint Analysis? Conjoint analysis is a popular method of product and pricing research that uncovers consumers' preferences and uses that information to help select product features, assess sensitivity to price, forecast market shares, and predict adoption of new products or services. 196 CU IDOL SELF LEARNING MATERIAL (SLM)

Conjoint analysis is a report of data &statistical analysis that company use in market research to understand how customers value different types or features of their products or services. It’s based on the principle that any product can be broken down into a set of attributes that ultimately impact users’ perceived value of an item or service. Conjoint analysis is typically conducted via a specialized survey that asks consumers to rank the value utility in a particular question. Analyzing the results allows the firm to then assign a value to each one. 13.6 METHODS OF CONJOINT ANALYSIS Conjoint analysis is the optimal market research approach for measuring the value that consumers place on features of a product or service. This commonly used approach combines real-life scenarios and statistical techniques with the modelling of actual market decisions. Types of conjoint analysis There are two main types of conjoint analysis: Choice-based Conjoint (CBC) Analysis and Adaptive Conjoint Analysis (ACA). Discrete choice-based conjoint (CBC) analysis: This type of conjoint study is the most popular because it asks consumers to imitate the real market’s purchasing behavior: which products they would choose, given specific criteria on price and features. For example, each product or service has a specific set of fictional characters. Some of these characters might be similar to each other or will differ. For instance, you can present your respondents with the following choice: Device 1 Device 2 6.7-inch Quad HD Super AMOLED Display  6.67-inch Quad HD AMOLED Display Qualcomm Snapdragon 855 chipset  Qualcomm Snapdragon 855 chipset 6GB RAM, 128 GB Storage  6GB RAM, 128 GB Storage Dual rear camera (12MP+16MP)  Triple rear camera (48MP+8MP+16MP) 4,000 mAh battery with 30w Dash Charging  2800mAh/3700mAh batteries The devices are almost identical, but device 2 has triple cameras with better configuration, and Device 1 has a higher battery power than Device 2. You would know how vital the trade- off between the number of cameras and battery capacity is by analyzing the responses. Using the discrete choice model, QuestionPro offers three design types to conduct conjoint analysis: 197 CU IDOL SELF LEARNING MATERIAL (SLM)

1. Random: This design displays random samples of the possible attributes. For each respondent, the survey software uniquely combines the characteristics. You can run a conjoint concept simulator to know what the choices that the tool will present when you deploy your survey. 2. D-Optimal: A flawlessly designed experiment helps researchers estimate parameters without minimum-variance and bias. A D-optimal design runs a few tests to investigate or optimize the subject under study. The algorithm helps to create a design that is optimal for the sample size and tasks per respondent. 3. Import design: You can also import designs in SPSS format. For example, QuestionPro lets you import fractional factorial orthogonal designs to make use of in surveys. Adaptive conjoint analysis (ACA): Researchers use this type of conjoint analysis often in scenarios where the number of attributes/features exceeds what can be done in a choice based scenario. ACA is great for product design and segmentation research, but not for determining the ideal price. For example, the adaptive conjoint analysis is a graded-pair comparison task, wherein the survey respondents are asked to assess their relative preferences between a set of attributes. Each pair is then evaluated on a predefined point scale. QuestionPro uses CBC, or Discrete Choice Conjoint Analysis, a great option if the price is one of the most critical factors for you or your customers. The method’s key benefit is that it provides a picture of the market’s willingness to make tradeoffs between various features. The result is an answer to what constitutes an “ideal” product or service. Level-up conjoint analysis insights Although conjoint analysis requires more involvement in survey design and analysis, the additional planning effort is often worth it. With a few extra steps, you get an authentic look into your most significant customer preferences when choosing a product. Price, for example, is vital to most folks shopping for a laptop. But how much more is the majority willing to pay for longer battery life for their laptop if it means a heavier and bulkier design? How much less in value is a smaller screen size compared to a slightly larger one? Using conjoint surveys, you’ll discover these details before making a considerable investment in product development. Conjoint is just a piece of the insights pie. Capture the full story with a cohesive pricing, consumer preference, branding, or go-to-market strategy using other question types and delivery methodologies to stretch the project to its full potential. With QuestionPro, you can build and deliver comprehensive surveys that combine conjoint analysis results with insights from additional questions or custom profiling information included in the survey. 198 CU IDOL SELF LEARNING MATERIAL (SLM)

13.7 IMPORTANCE OF CONJOINT ANALYSIS What is conjoint analysis used for? The insights a company gleans from conjoint analysis of its product features can be leveraged in several ways. Most often, conjoint analysis impacts pricing strategy, sales and marketing efforts, and research and development plans. Conjoint analysis is used in a wide range of different market research and insight applications from copy testing, to pricing research to product and service design, to defining membership schemes. The list of applications is relatively long as conjoint gets adapted to different purposes. For instance it's possible to use some of the design principles to develop and test areas like website or promotional message design using live in-market testing. Below is a list of common uses. Main Applications of Conjoint Analysis Ready to dive further into conjoint analysis? In this post I describe the main applications of choice-based conjoint analysis (choice modeling; CBC). If you haven’t yet, check out “Conjoint Analysis: the Basics” for a primer on Choice-Based- Conjoint Analysis. Testing the appeal of a new product Choice-based conjoint analysis is widely used for testing the appeal of a new products and services. For example, a new flavor of soft drink, a new cabin in an aircraft (premium economy), or a new transport option (hyper loop). It is generally preferred to simple techniques like concept tests, because:  By presenting the various attributes of the alternatives, it encourages people to think through the trade-offs.  We get a deeper understanding of why people make decisions.  We can test the effects of lots of different possible products, rather than having to lock in a particular concept for testing prior to collecting any data. Understanding product deletions Choice-based conjoint analysis can be used to work out what happens when a product is removed (deleted) from a market. The main focus here, is on understanding what customers buy if they cannot buy their existing alternative. This is particularly useful in situations where a company has a large collection of brands or SKUs. Choice-based conjoint done for this purpose tends to use a special type of experimental design known as an availability design, where the list of which brands or SKUs are shown varies from question to question. This is useful both in terms of portfolio planning and also in terms of understanding antitrust/monopoly cases. 199 CU IDOL SELF LEARNING MATERIAL (SLM)

Portfolio optimization Understanding product deletions naturally leads into designing optimal portfolios of products. For example, if a choice model is conducted in the phone market, and estimates preferences for all the key attributes (screen size, weight, price, etc.), then optimization techniques can be used to identify, say, the four best models of phone to make. This can be done with a focus either on market share or profit maximization. Assessing the impact of changes in product design Choice-based conjoint analysis is widely used to prioritize changes to product design, where the changes could be improvements (e.g., better packaging), or reductions in performance levels (e.g., less legroom on flights, replacing natural with nature-identical ingredients). Most commonly, this occurs as a part of a more general business case, where the choice model estimates the demand for the product and an economic analysis works out the impact on profit. Fig. 13.1 Pricing optimization Choice-based conjoint analysis is widely used as an input to pricing, in terms of working out the impacts of price increases and decreases, as well as understanding how changes in price influence cannibalization. It is common to use choice models to compute willingness-to-pay, which is used as an input to policy making decisions in economics and damage assessments in legal actions. For example, this approach has been used in working out damages in environmental cases (where, say, the damage of an oil leak can be viewed as a change in the product design of the environment), copyright cases in terms of the value of illegally used copyrighted materials, and patent violations, such as in the phone wars between Apple and Samsung. 200 CU IDOL SELF LEARNING MATERIAL (SLM)