A0236
Title: Risk factor detection with methods from explainable ML
Authors: Natalie Packham - Berlin School of Economics and Law (Germany) [presenting]
Abstract: The importance of risk management in the financial industry has increased rapidly since the financial crisis, particularly regarding financial market stability. A particular focus is on stress testing methods, which capture portfolio risk under adverse conditions. Advances in statistical learning and the availability of large, granular data sets offer new methodological possibilities for stress testing. Financial risk management applications such as hedging, scenario analysis and stress testing rely on portfolio models based on risk factors. In addition to observable risk factors, factor models with non-observable, data-based factors offer interesting alternatives. However, the lack of interpretability of the output is limiting. Time-dynamic methods are developed for the interpretability of principal components (PCA) and autoencoders, allowing for aggregated risk factors from existing risk factors. This aggregation allows for plausibly implementing less granular and even global stress scenarios.
