Long-Short-Term Memory Neural Networks in Varying Regimes

Combining Regime Shifts and Machine Learning Models in Financial Risk Management

September 28, 2022 | 6:00 PM - 9:00 PM

123 Street Location

Overview

In-person or virtual attendance available


Machine learning (ML) models are now widely applied to understand and predict patterns in financial markets. Classification trees and artificial neural networks are popular choices for modelling market behavior and risk measures. ML models are powerful tools, but must be handled with care to produce interpretable and reliable results for risk managers. 

As data-driven decision processes made their way into risk management, estimation and model identification issues have arisen. These might result from too much or too little data and be reinforced by model choices that are inappropriate given the prevailing market conditions.

In this presentation, time series analysis and ML approaches are combined to find models best suited for forecasting financial time series. Hidden Markov Models (HMM) are detected in observed financial time series and are subsequently incorporated into a long-short-term memory neural network (LSTM). Through this, we develop a model to forecast corporate credit spreads over changing market regimes within an LSTM. Switching regimes are included as a feature to the neural network. This HMM-LSTM model is calibrated to corporate credit spreads of three European countries. The performance of the LSTM is compared to the accuracy of an LSTM without regime-switching information. Furthermore, we propose an HMM-LSTM mixture of experts’ model, where regime-switching information assumes a gating function to activate a neural network. Applications of this approach to time series forecasting in electricity markets are shown. The findings demonstrate that in most cases the LSTM performance is improved when regime information is added.


Venue

Deutsche Bank AG
Unter den Linden 13-15, 10117 Berlin

Register Now

Contact

Questions can be directed to GARP Events at events@garp.com.

Agenda

*Date and Time noted as

September 28, 2022

6:00 PM - 6:30 PM

Registration

6:30 PM - 6:35 PM

Welcome and Introductions

6:35 PM - 7:15 PM

Presentation

View Details

Speakers

Prof. Dr. Christina Erlwein-Sayer, Professor of Statistics and Financial Mathematics,

7:15 PM - 7:30 PM

Audience Q&A

7:30 PM - 9:00 PM

Networking Reception

Speakers/Moderators

Prof. Dr. Christina Erlwein-Sayer

Prof. Dr. Christina Erlwein-Sayer
Professor of Statistics and Financial Mathematics,

BylawsCode of ConductPrivacy NoticeTerms of Use © 2022 Global Association of Risk Professionals