Machine Learning in Finance and Insurance
This course introduces machine learning methods that can be used in finance and insurance applications.
Lecturers: Patrick Cheridito, Stephan Eckstein and Gabriele Visentin
Wednesdays from 10:15 – 11:55 in ML H44
Exercise Sessions Wednesdays from 12:15 – 13:00 in HG E1.1
Prerequisites Basic knowledge in analysis, linear algebra and probability theory
Slides and Exercise Sheets are on Moodle
This course introduces different machine learning methods and discusses their application to problems in finance and insurance. Topics include linear, polynomial, logistic, ridge regression, SVD, SDG, dimension reduction, RKHS, kernel regression, classification with kernels, clustering, SVM, CART, random forests, XGBoost, neural networks, batch normalization, regularization, transformers, option valuation, credit models, insurance loss models, deep hedging.
Syllabus
- Linear regression
- polynomial regression
- logistic regression
- ridge regression
- SVD
- SDG
- dimension reduction
- RKHS
- kernel regression
- classification with kernels
- clustering
- SVM
- CART
- random forests
- XGBoost
- neural networks
- batch normalization
- regularization
- transformers
- option valuation
- credit models
- insurance loss models
- deep hedging