MBM433 Customer Analytics in a Digital World

• Topics

  Many firms collect massive amounts of data about the digital behavior of customers in addition to targeted marketing research on perceptions and evaluations of products and services. The question is how to use these individual-level data to produce valuable customer insights and use them to acquire, retain, and satisfy customers? These are core elements of customer analytics. In this course, students will learn how to find answers to important questions asked by managers, such as:

  • Which customers should we target?
  • Why do customers choose one brand over another?
  • How likely is it that a customer will drop out?
  • Which customers should we try to keep/let go?
  • What is the "life-time" value of a customer?

  The taught topics include:

  1. Introduction to Customer Analytics and Model Building Process
  2. Recency-Frequency-Monetary (RFM) analysis
  3. Logistic Regression
  4. Decision Trees
  5. Multinomial and Ordered Logit
  6. Conjoint Analysis
  7. Introduction to natural language processing (NLP) and text analytics
  8. Introduction to neural network research and social network analysis
  9. Modeling challenges in customer analytics (especially in a digital world)

• Learning outcome

  This course will cover the basic knowledge about customer analytics and the relevant concepts, as well as some of the most commonly used types of model to analyze customer behavior. After completing the course, students will be able to:

  Knowledge

  • Describe the basics of customer analytics and relevant concepts such as customer lifetime value and customer heterogeneity.
  • Explain important customer behaviors and know how to collect data to analyze them.
  • Recall when a given type of customer model should be used and why.

  Skills

  • Perform some commonly used customer models using R.
  • Interpret and give intuitive explanation for the results of different customer models.
  • Perform model evaluation and model selection.
  • Adjust the specification of different models to fit real-world data.

  General Competence:

  • Use analytical thinking to solve real-world business problems.
  • Differentiate between different types of customer models and know when and how to use them properly.
  • Communicate key results/insights from customer models to general audience.
  • Make informed decision based on customer analytics.

• Teaching

  The course format: Regular lectures and lab sessions/tutorials where students work on group-based exercises/assignments. 

  All necessary information will be provided on Canvas and it is assumed that students are aware of all course-related information posted on Canvas. 

  Regular lectures provide students with theoretical knowledge about customer analytics concepts and a basic understanding of different customer models. Practical/modeling skills will be gained through a set of group-based hands-on exercises and assignments.

  Note that students are required to work in groups in this course and it is students' responsibility to find and join a group of 2-4 persons. Students can search for group members through Canvas or using their own ways. 

• Recommended prerequisites

  To take this course, you should have basic skills in R programming language and data analysis similar to those obtained in MBM437, MBM400A, or similar introductory courses from other profiles.

• Credit reduction due to overlap

  None

• Compulsory Activity

  To attend the final assessment, students will need to complete a course-approval assignment in the middle of the course. Students must submit their solutions in groups that contain from 2 to 4 students. 

  Compulsory activities (work requirements) are only valid in the semester that the student attends the lectures.

• Assessment

  Group-based term paper (group size 2-4). The term paper must be written in English.

• Grading Scale

  A-F

• Computer tools

  R (and RStudio), a working laptop for lab sessions.

• Literature

  Compendium of selected articles and book chapters.