Course: Machine Learning in Finance, Management and Accounting (5106-842)

Persons:

• Amirhossein Sadoghi (verantwortlich)

Type of Course:

lecture with exercise

In-Class Hours Per Week:

3

Contents:

The course starts with an overview of some principles of statistics, as well as a brief review of software R. The course covers some methods related to classification, clustering, and deep learning as well as text mining techniques. Finally, applications of such techniques in finance and management will be discussed.

Literature:

An Introduction to Statistical Learning with Applications in R.
by: James, G., Witten, D, D., hastie, T., Tibshirani, R.

Big Data and Social Science: A Practical Guide to Methods and Tools, 1st Edition by Ian Foster, Rayid Ghani, Ron S. Jarmin, Frauke Kreuter, Julia Lane

Location:

Hohenheim

Remarks:

In this course, we are working on a range of techniques to create scientific models from empirical data. A large part of the course will be in block format. The course consists of several lectures on data mining techniques with following some exercises in the class. The teaching style of this course is a research-oriented approach (mostly, empirically rather than theoretically). Several lab exercises, based on scientific papers, are designed to introduce the application of data mining in social sciences. Students will learn how to work the big dataset and apply some advanced techniques in their own research field. The basic knowledge of statistics or econometrics is sufficient. After completing the course, students shall be able to independently draft an academic paper on the Ph.D. level on key issues of big data in social sciences.

Module:

• 5105-840 Elective Module (semi-elective)