Detecting Changes in Asset Co-Movement Using the Autoencoder Reconstruction Ratio

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.

[1]  Liran Goshen,et al.  Unsupervised Abnormality Detection through Mixed Structure Regularization (MSR) in Deep Sparse Autoencoders , 2019, Medical physics.

[2]  Alexei Kondratyev,et al.  Learning Curve Dynamics with Artificial Neural Networks , 2018 .

[3]  KyungHyun Cho,et al.  Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Noisy Images , 2013 .

[4]  N. Shephard,et al.  Estimating quadratic variation using realized variance , 2002 .

[5]  Raja Giryes,et al.  Autoencoders , 2020, ArXiv.

[6]  S. Poon,et al.  Financial Modeling Under Non-Gaussian Distributions , 2006 .

[7]  Frank J. Fabozzi,et al.  The ICA-based Factor Decomposition of the Eurozone Sovereign CDS Spreads , 2015 .

[8]  Sébastien Page,et al.  Principal Components as a Measure of Systemic Risk , 2010, The Journal of Portfolio Management.

[9]  Fulvio Corsi,et al.  A Simple Approximate Long-Memory Model of Realized Volatility , 2008 .

[10]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[11]  Neil Shephard,et al.  Multivariate High-Frequency-Based Volatility (HEAVY) Models , 2012 .

[12]  Andrew W. Lo,et al.  Measuring Systemic Risk in the Finance and Insurance Sectors , 2010 .

[13]  Boris Podobnik,et al.  Changes in Cross-Correlations as an Indicator for Systemic Risk , 2012, Scientific Reports.

[14]  Increased Correlation Among Asset Classes: Are Volatility or Jumps to Blame, or Both? , 2016 .

[15]  R. Campbell,et al.  Increased Correlation in Bear Markets , 2002 .

[16]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[17]  Bryan T. Kelly,et al.  Autoencoder Asset Pricing Models , 2019, Journal of Econometrics.

[18]  R. Engle,et al.  Asymmetric Dynamics in the Correlations of Global Equity and Bond Returns , 2003, SSRN Electronic Journal.

[19]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[20]  Yan Liu,et al.  Low-dose CT restoration via stacked sparse denoising autoencoders , 2018, Neurocomputing.

[21]  Hardy Ct The center for research. , 1981 .

[22]  Yacine Ait-Sahalia,et al.  Increased Correlation Among Asset Classes: Are Volatility or Jumps to Blame, or Both? , 2014 .

[23]  Stephen J. Roberts,et al.  Dynamically Measuring Statistical Dependencies in Multivariate Financial Time Series Using Independent Component Analysis , 2013 .

[24]  Mico Loretan,et al.  Evaluating Correlation Breakdowns During Periods of Market Volatility , 2000 .

[25]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[26]  I. Rezek,et al.  Stochastic complexity measures for physiological signal analysis , 1998, IEEE Transactions on Biomedical Engineering.

[27]  D. Helbing,et al.  Quantifying the Behavior of Stock Correlations Under Market Stress , 2012, Scientific Reports.

[28]  N. Packham,et al.  A factor-model approach for correlation scenarios and correlation stress testing , 2018, Journal of Banking & Finance.

[29]  Xiye Yang,et al.  Testing for Mutually Exciting Jumps and Financial Flights in High Frequency Data , 2017 .