Semester:SS 24
Type:Module/Course/Examination
Language:English
ECTS-Credits:3.0
Scheduled in semester:2
Semester Hours per Week / Contact Hours:30.0 L / 22.5 h
Self-directed study time:67.5 h
Type:Module/Course/Examination
Language:English
ECTS-Credits:3.0
Scheduled in semester:2
Semester Hours per Week / Contact Hours:30.0 L / 22.5 h
Self-directed study time:67.5 h
Module coordination/Lecturers
- Ass.-Prof. Dr. Sebastian Stöckl
(Modulleitung)
Curricula
Master's degree programme in Finance (01.09.2020)Description
- The course Innovative Finance: Data Science and Machine Learning 1 will give students the understanding and necessary tools to apply Machine Learning methods to essential research problems in finance.
- Statistical learning (aka Machine Learning or Artificial Intelligence) is the main driver of innovation in the financial industry and can be found almost everywhere: credit decisions, risk management, fraud prevention or (automated) investment processes.
- Therefore, this course will pick up where Quantitative Finance stopped and further explore methods of supervised and unsupervised learning, thereby teaching our computers to learn from the large amounts of data available to us.
- The entire course will be accompanied by (small) real-world-real-data applications making use of Googles’ free and powerful Colab and Kaggle platform.
- For those with a further interest in Innovative Finance: Join Innovative Finance: Data Science and Machine Learning 2 for a real and big-data based machine learning challenge, entirely hosted on www.kaggle.com.
In particular, this course will cover:
- Linear model selection and regularization
- Resampling methods, model assessment and selection
- Tree-based methods
- Neural networks and deep learning
- Unsupervised learning
Learning Outcomes
After successful completion of the course:
- Students understand and can explain the concepts of supervised and unsupervised learning.
- Students are familiar with a variety of topics in finance where machine learning methods can be successfully applied.
- Students are able to apply the most important concepts covered in the course to real datasets in R, making use of powerful online platforms.
- Students are able to effectively communicate about machine learning and artificial intelligence in finance.
- Students are able to critically evaluate situations where machine learning could successfully be applied.
Qualifications
Lectures Method
- Lectures are interactive
- Moodle is used throughout the course to disseminate course material and for information and discussion.
Exam Modalities
see lecture(s) within the module
Exams
- PWW-MA_Innovative Finance: Data Science and Machine Learning I SE (SS 24, bewertet)