Microstructure in the Machine Age

63 Pages Posted: 25 Mar 2019

See all articles by David Easley

David Easley

Cornell University - Department of Economics; Cornell University - Department of Information Science

Marcos Lopez de Prado

Harvard University

Maureen O'Hara

Cornell University - Samuel Curtis Johnson Graduate School of Management

Zhibai Zhang

New York University (NYU) - NYU Tandon School of Engineering

Date Written: February 28, 2019

Abstract

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.

Keywords: Market Microstructure, Machine Learning, Features Importance, MDI, MDA, Futures

JEL Classification: C02, D52, D53, G14, E44

Suggested Citation

Easley, David and de Prado, Marcos Lopez and O'Hara, Maureen and Zhang, Zhibai, Microstructure in the Machine Age (February 28, 2019). Available at SSRN: https://ssrn.com/abstract=3345183 or http://dx.doi.org/10.2139/ssrn.3345183

David Easley (Contact Author)

Cornell University - Department of Economics ( email )

414 Uris Hall
Ithaca, NY 14853-7601
United States
607-255-6283 (Phone)
607-255-2818 (Fax)

Cornell University - Department of Information Science ( email )

402 Bill & Melinda Gates Hall
Ithaca, NY 14853
United States

Marcos Lopez De Prado

Harvard University

1875 Cambridge Street
Cambridge, MA 02138
United States

Maureen O'Hara

Cornell University - Samuel Curtis Johnson Graduate School of Management ( email )

Ithaca, NY 14853
United States
607-255-3645 (Phone)
607-255-5993 (Fax)

Zhibai Zhang

New York University (NYU) - NYU Tandon School of Engineering ( email )

6 MetroTech Center
Brooklyn, NY 11201
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
4,047
Abstract Views
9,459
Rank
4,808
PlumX Metrics