Actionable Customer Analytics-M-

Actionable customer analytics is aboutmaking data-informed or data driven business decisions.In making these decisions, managers choose from among alternative courses of action in a complex and uncertain world. Eventually, they enable the creation of business intelligence through customer insights, i.e., better decisions through a better understanding of the customer behavior.

In this master course, we will work with the most essential data analysis technique on a range of artifical and read data sets. These techniques include regression, logistic regression, and k-means. However, the focus is not on the method alone, but in particular on translating the results into recommendations for management decisions.

Using various types of data sources, models, and related exercises tied to recommended software components, course participants will develop marketing plans in various decision contexts.

The preliminary course plan is:

Week 1: Introduction + data briefing

Week 2: Descriptive analytics, regression, and JMP

Week 3: Logistic regression and actionable customer analytics

Week 4: Assumptions& K-means method

Week 5: K-means method (continued) & guest talk

Week 6: Nudging & steering customers

Week 7: Scraping

Week 8: Dark side of data analytics & guest talk

The content of this course is mainly based on the lecture slides. Selected articles are provided, but the main resources for learning are lecture slides, exercises and hands-on sessions on the software Excel, JMP (SAS), and Grepsr.

During the course, we will use in particular Excel and JMP(belonging to SAS). Licenses for JMP will be provided free of charge to course participants.

In the later sessions, we will briefly look at alternative software, such as Grepsr for scrapping, python and Jupiter-files. Experience in using Excel is expected, nevertheless, this course is designed such that participants without any experience in JMP, Pythin or Gepsr will be able to complete all assignments.

Content-wise, we will apply a mixture of traditional teaching methods, hands-on assignments, applied on real-world data sets.

~20% assignments

~30% report

~50% exam

150