Detecting changes in asset co-movement using the autoencoder reconstruction ratio

ARR aims to anticipate volatility patterns to provide signals for risk management and trading

CLICK HERE TO VIEW THE PDF

Detecting changes in asset co-movements is of great importance to financial practitioners, with numerous risk management benefits arising from the timely detection of breakdowns in historical correlations. Bryan Lim, Stefan Zohren and Stephen Roberts propose a real-time indicator to detect temporary increases in asset co-movements that they call the autoencoder reconstruction ratio (ARR), which measures how well a basket of asset returns can be modelled using a lower