VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Marketing Analytics
Last Updated: 2026-02-05 16:23:40
Abstract
Students will use extensive customer data from an insurance company in order to develop prediction models for e.g. customer revenue and churn in a prediction challenge.
Objective
- Participants of this class will gain an understanding, how value can be generated out of customer data. - Participants will learn how to prepare real customer data. - Participants will be able to develop prediction models autonomously.
Content
The class will be held by Sebastian Tillmanns (Chair of Technology Marketing). The students will work in groups and give a final presentation. Students of this class will gain an understanding how to extract value from customer data autonomously by participating in a prediction competition. Therefore, they receive real customer data from an insurance company. Students are free to prepare the provided data and develop prediction models in the way they consider the best. Their freedom of choice covers all statistical methods, software packages and data that are available to them. At the end of the class, their predictions will be compared with the real development of the customers in the provided sample. Furthermore, students will give final presentations at the end of the class, which will be joined by representatives of the insurance company. Students will have to write a short paper, in which they describe how they proceeded. We expect that students test different prediction models against each other to justify their proceeding. At the beginning of the class, students will be able to visit several lectures, which will help to work on the given prediction task. These lectures involve fundamentals of marketing analytics and data analytics with common software packages. Throughout the lecture, several time slots are provided, where students can discuss their prediction models with the lecturers. The data handling and prediction skills students achieve in this class are not limited to marketing applications, but can be easily extended to other fields where predications of continuous or binary metrics are useful.
General Information
- Language
- English
- Levels
- MSC
- Frequency
- Yearly recurring
Examination
- Type
- graded semester performance
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| seminar |
Marketing Analytics
Irregular lecture
|
|
24 h semesterly |