There are two main things which make returning for Open Programs such a valuable and worthwhile experience. The first is being back on campus – meeting the current students, returning to campus again, the whole experience was just so pleasant. The second is the level of quality in the courses – the faculty teaching are absolute experts.
Over the last couple of years, we have seen a resurgence of interest in Machine Learning applications by researchers and practitioners alike. The most considerable breakthroughs have occurred in the subfield of Deep Learning – a collection of Machine Learning methods inspired by the workings of the human brain. Today, Deep Learning is at the heart of many state-of-the-art (predictive) analysis tools providing a competitive edge to organizations, especially in the financial industry. Examples include, credit default prediction, pattern recognition, stock price prediction, sentiment analyses, outlier detection, and natural language processing, to name only a few.
The course introduces Deep Learning methods including Feed Forward Neural Networks, Convolutional Neural Networks, and Recurrent Neural Networks. Learned methods will be applied to problems such as credit default, customer churn, and stock price predictions. Against the background of recent debates and regulations concerning the “black box” nature of Deep Learning applications, the course will also touch upon interpretability methods.
This course is offered in the part-time Master in Finance program and may be attended on a “no credit” basis by individuals not enrolled in the program. Course participants are visitors who are not responsible for assignments and do not take an exam or earn academic credits. As the number of seats in the course is limited, we recommend to register online early.
Upon completion of this course, you will:
Learn about the inner workings of Deep Learning techniques.
Learn how to handle and pre-process data in Python using popular libraries such as Pandas, NumPy, Scikit-Learn.
Learn how to build Deep Learning models in Python using TensorFlow.
Apply what they have learned to real data sets.
Feed Forward Networks, Convolutional Networks, Recurrent Networks
Data analysis in Python
Kevin Bauer is a post-doctoral researcher at the Leibniz Institute for Financial Research SAFE since 2020. At SAFE he is part of the “Digitization of the Financial Industry”-research group. His research focuses on human-machine interaction, human-centric machine learning, and human information processing. Kevin Bauer received his Ph.D. in Economics from Goethe University in 2018. In 2020, he obtained a Master’s in Information Systems with a focus on machine learning and artificial intelligence from Goethe University. Before joining SAFE, Kevin Bauer worked at the Startup and Innovation Center, TechQuartier as an Artificial Intelligence (AI) specialist, where he is still active as an external consultant and lecturer on AI related topics.
Course materials will be provided in electronic form.
Partially online via Zoom and Campus Westend of Goethe University Frankfurt.
A GBS certificate of participation is awarded upon completion of the course.
€ 950 (fee is exempt from VAT). The fee for GBS students or alumni amounts to € 400.
*Withdrawal and fee refund
In case the course withdrawal request is received two weeks prior to the start of classes, GBS will retain a withdrawal fee of €50. In case the course withdrawal request is received less than two weeks prior to the start of classes, GBS will retain 50% of the payment made.
|Offered in SS 2022|