The module gives students an opportunity to work on a real-life predictive modeling project. The specific modeling task will typically relate to a business planning problems, for example in marketing or finance. In this scope, students have the opportunity to develop a variety of skills, including:
- Students further develop their team work and project management abilities.
- Students get acquainted with contemporary software packages for data science.
- Students are able to develop advanced forecasting models using a variety of algorithms from statistics, machine learning, and other domains.
- Students advance their knowledge in data integration, preparation, and transformation, which allows them to create predictive variables from noisy real-world data sets.
In the first part of the seminar, students will develop an entry for a selected forecasting competition. In this scope, they will experience several typical challenges that arise in real-world modeling projects, and develop the necessary skills to overcome these obstacles.
During the competition (i.e., in the first part of the course), which typically runs from the start of the semester to mid-May, seminar participants must be prepared to work under a tight deadline. It is expected that every participants invest substantial effort and time to contribute to the team's submission.
In the second part of the seminar, students will further advance the solution developed for the competition. To that end, they will receive specific analytic tasks and/or research questions related to the problem studied in the competition. Corresponding solutions will be submitted in the form of a research paper. Assessment of student performance will be based on this paper.
Max. number of participants: 24
Application: 1.02. - 14.04.2020 on AGNES
If there are more than 24 applicants, seminar places will be assigned by draw.
Hastie, T.; Tibshirani, R.; Friedman, J. (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Eds., Springer.
StO/PO MA 2016: 6 LP, Modul: "Applied Predictive Analytics"
StO/PO MEMS 2016: 6 LP, Modul: "Applied Predictive Analytics", Major: Quantitative Management Science