Detecting Changes in Asset Co-Movement Using the Autoencoder Reconstruction Ratio
This addresses risk management for financial practitioners by providing a real-time indicator for asset co-movement changes, though it is incremental as it builds on existing methods like the Absorption Ratio.
The paper tackled detecting changes in asset co-movements in finance by proposing the Autoencoder Reconstruction Ratio (ARR), which uses a deep sparse denoising autoencoder to replace PCA, showing that lower ARR values coincide with higher volatility and larger drawdowns, and improving short-term predictors for volatility and market crashes.
Detecting changes in asset co-movements is of much importance to financial practitioners, with numerous risk management benefits arising from the timely detection of breakdowns in historical correlations. In this article, we propose a real-time indicator to detect temporary increases in asset co-movements, the Autoencoder Reconstruction Ratio, which measures how well a basket of asset returns can be modelled using a lower-dimensional set of latent variables. The ARR uses a deep sparse denoising autoencoder to perform the dimensionality reduction on the returns vector, which replaces the PCA approach of the standard Absorption Ratio, and provides a better model for non-Gaussian returns. Through a systemic risk application on forecasting on the CRSP US Total Market Index, we show that lower ARR values coincide with higher volatility and larger drawdowns, indicating that increased asset co-movement does correspond with periods of market weakness. We also demonstrate that short-term (i.e. 5-min and 1-hour) predictors for realised volatility and market crashes can be improved by including additional ARR inputs.