Prediction with Expert Advice for Value at Risk. / Dzhamtyrova, Raisa; Kalnishkan, Yuri.

Proceedings of The 2020 International Joint Conference on Neural Networks (IJCNN 2020). IEEE, 2020.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Documents

Abstract

We propose to apply the method of online prediction with expert advice for estimation of Value at Risk. We show that in some cases the combination of different methods can produce better results compared to a single model. Our approach is based onWeak Aggregating Algorithm (WAA), which is similar to the Bayesian method, where the prediction is the average over all models based on the likelihood of the available data. WAA provides a theoretical guarantee that the prediction strategy is asymptotically as good as the best expert. We propose two ways of combining predictions of different experts. The first approach combines predictions of normal distribution experts, whereas the second method combines predictions of conventional models that are used to estimate Value at Risk. The experimental results on three stocks show that WAA performs close to or better than the best expert model. In addition, backtesting with Kupiec unconditional coverage test and Christoffersen conditional coverage test shows that WAA is the only method that fails to reject the null hypothesis for all test cases.
Original languageEnglish
Title of host publicationProceedings of The 2020 International Joint Conference on Neural Networks (IJCNN 2020)
PublisherIEEE
Number of pages8
ISBN (Electronic)978-1-7281-6926-2
ISBN (Print)978-1-7281-6927-9
DOIs
Publication statusPublished - 28 Sep 2020
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 38146563