Discriminating modelling approaches for Point in Time Economic Scenario Generation
This addresses the need for more responsive economic forecasting tools for financial analysts, though it is incremental as it builds on existing models applied to a new formulation.
The paper tackled the problem of generating economic scenarios that quickly adapt to market changes by comparing four modeling approaches for Point in Time Economic Scenario Generation, finding that generative networks, especially the conditional Variational Autoencoder, outperformed traditional methods in statistical tests and backtesting with more robust and computationally efficient performance.
We introduce the notion of Point in Time Economic Scenario Generation (PiT ESG) with a clear mathematical problem formulation to unify and compare economic scenario generation approaches conditional on forward looking market data. Such PiT ESGs should provide quicker and more flexible reactions to sudden economic changes than traditional ESGs calibrated solely to long periods of historical data. We specifically take as economic variable the S&P500 Index with the VIX Index as forward looking market data to compare the nonparametric filtered historical simulation, GARCH model with joint likelihood estimation (parametric), Restricted Boltzmann Machine and the conditional Variational Autoencoder (Generative Networks) for their suitability as PiT ESG. Our evaluation consists of statistical tests for model fit and benchmarking the out of sample forecasting quality with a strategy backtest using model output as stop loss criterion. We find that both Generative Networks outperform the nonparametric and classic parametric model in our tests, but that the CVAE seems to be particularly well suited for our purposes: yielding more robust performance and being computationally lighter.