Course 2026-2027 a.y.

Course topics:

This list is tentative - some topics may be modified or added on the syllabus.

1. Foundations — what marketing analytics is for; the value framework (value to the firm, the customer, and society); the marketing data landscape (transaction, customer, digital-trace, and text data); etc.
2. Acquire — who to go after. Customer segmentation, positioning and perceptual mapping, and listening to markets through text (reviews, social) and AI-mediated discovery.

3. Convert — what makes customers buy. Response and choice models, recommendation systems, and pricing and promotion analysis.
4. Grow — making customers more valuable. Customer lifetime value, cross-sell and up-sell targeting, and the use of generative AI for personalization.
5. Retain — keeping customers. Churn modeling, customer-value management, and text analytics on complaints and feedback to diagnose why customers leave.
6. Measure — did any of it work. Experiments and A/B testing, plus quasi-experimental methods for when experiments are not possible.

- Translate a marketing problem into an analytics question

- Prepare and explore marketing data in Python 
- Segment and position customers and products
- Build and interpret predictive models for customer decisions
- Analyze pricing, promotion, and campaign effects
- Apply text and generative-AI methods to marketing
- Communicate analytical findings as marketing recommendations

• Analyze and interpret customer decisions using panel data.
• Analyze customer profitability and brand equity.
• Prioritize customers and select appropriate actions across different segments.
• Analyze firm marketing decisions (e.g., advertising) and measure its performance.
• Analyze consumers and firm decisions in online contexts.

• Lectures
• Practical Exercises
• Collaborative Works / Assignments

All methods other than face-to-face lectures are used to provide exercises and examples of the application of theoretical concepts and models.

With the purpose of measuring the acquisition of the above-mentioned learning outcomes, the students’ assessment is based on the following main components:

*Group Assignment (40%)

Designed to assess students’ ability to identify marketing problems, analyze customer or firm decisions using panel data, and propose actionable solutions. Students will apply

selected methods and tools from the course to real-world marketing analytics challenges, gaining hands-on experience in problem-solving and data interpretation.

*Written Exam (50%)

The exam includes a mix of open- and closed-ended questions aimed at evaluating students’ understanding of consumer data analytics, customer management principles,

and their ability to apply analytical methods to various marketing scenarios.

*Class Participation (10%)

Active engagement in class discussions, exercises, and case analyses contributes to the participation grade.

Written Exam (100%)

The exam includes a mix of open- and closed-ended questions that covers all chapters of the text book. The exam aims to assess students’ understanding of the mechanisms of consumer data analytics as well as principles of customer and marketing management.

• Lecture notes
• Hand-outs

Recommended Reference:

Hwang & Burtch - Machine Learning and Generative AI for Marketing: Take your data-driven marketing strategies to the next level using Python, Packt Publishing, 2024 (selected chapters)

Textbook for non-attending students:

Peter C. Verhoef, Edwin Kooge, and Natasha Walk (2016), Creating Value with Big Data Analytics: Making Smarter Marketing Decisions, Routledge; ISBN-10: 9781138837973; ISBN-13: 978-1138837973