Microstructure in the Machine Age

We demonstrate how a machine learning algorithm can be applied to predict and explain modern market microstructure phenomena. We investigate the efficacy of various microstructure measures and show that they continue to provide insights into price dynamics in current complex markets. Some microstructure features with apparent high explanatory power exhibit low predictive power, and vice versa. We also find that some microstructure-based measures are useful for out-of-sample prediction of various market statistics, leading to questions about the efficiency of markets. Our results are derived using 87 of the most liquid futures contracts across all asset classes.

[1]  Alberto G. Rossi Predicting Stock Market Returns with Machine Learning , 2018 .

[2]  R. Philip,et al.  Estimating Permanent Price Impact via Machine Learning , 2019, Journal of Econometrics.

[3]  The Volume Clock: Insights into the High-Frequency Paradigm , 2012, The Journal of Portfolio Management.

[4]  Joel Hasbrouck,et al.  Trading Costs and Returns for U.S. Equities: Estimating Effective Costs from Daily Data , 2009 .

[5]  Oleg Bondarenko,et al.  Assessing Measures of Order Flow Toxicity and Early Warning Signals for Market Turbulence , 2014 .

[6]  Sendhil Mullainathan,et al.  Machine Learning: An Applied Econometric Approach , 2017, Journal of Economic Perspectives.

[7]  Hal R. Varian,et al.  Big Data: New Tricks for Econometrics , 2014 .

[8]  David Easley,et al.  Flow Toxicity and Liquidity in a High Frequency World , 2012 .

[9]  R. Engle,et al.  Predicting VNET: A model of the dynamics of market depth , 2001 .

[10]  Mao Ye,et al.  Sparse Signals in the Cross-Section of Returns , 2017, The Journal of Finance.

[11]  Pavel Savor,et al.  Earnings Announcements and Systematic Risk , 2015 .

[12]  Maureen O'Hara,et al.  Time and the Process of Security Price Adjustment , 1992 .

[13]  Roberto Rigobon,et al.  The Billion Prices Project: Using Online Prices for Measurement and Research , 2016 .

[14]  David Easley,et al.  Liquidity, Information, and Infrequently Traded Stocks , 1996 .

[15]  Maureen O'Hara,et al.  High frequency market microstructure. , 2015 .

[16]  Richard Roll,et al.  Commonality in Liquidity , 1999 .

[17]  Maureen O'Hara,et al.  OPTIMAL EXECUTION HORIZON , 2012 .

[18]  HERBERT A. SIMON,et al.  The Architecture of Complexity , 1991 .

[19]  Alberto Abadie,et al.  The risk of machine learning , 2017, 1703.10935.

[20]  Y. Amihud,et al.  Illiquidity and Stock Returns II: Cross-Section and Time-Series Effects , 2018, The Review of Financial Studies.

[21]  Tālis J. Putniņš,et al.  High frequency trading and comovement in financial markets , 2019, Journal of Financial Economics.

[22]  Earnings Announcements and Systematic Risk , 2016 .

[23]  David Easley,et al.  Discerning Information from Trade Data , 2015 .

[24]  A. Storeygard,et al.  The View from Above: Applications of Satellite Data in Economics , 2016 .

[25]  Duane J. Seppi,et al.  Comments welcome , 1998 .

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

[27]  Terry A. Marsh,et al.  BV-VPIN: Measuring the Impact of Order Flow Toxicity and Liquidity on International Equities Markets , 2016 .

[28]  A. Kyle Continuous Auctions and Insider Trading , 1985 .

[29]  D. Bernhardt,et al.  Trade-Time Measures of Liquidity , 2017 .

[30]  D. Bernhardt,et al.  Trade-time based measures of liquidity , 2016 .

[31]  Bidisha Chakrabarty,et al.  Short sales, long sales, and the Lee–Ready trade classification algorithm revisited ☆ , 2012 .

[32]  Maureen O'Hara,et al.  OPTIMAL EXECUTION HORIZON , 2015 .

[33]  Pavel Savor,et al.  Asset Pricing: A Tale of Two Days , 2013 .

[34]  Nicolas Huck,et al.  Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500 , 2017, Eur. J. Oper. Res..

[35]  R. Roll,et al.  A Simple Implicit Measure of the Effective Bid-Ask Spread in an Efficient Market , 2008 .

[36]  Shane A. Corwin,et al.  A Simple Way to Estimate Bid-Ask Spreads from Daily High and Low Prices , 2011 .