A Data Science Solution to the Multiple-Testing Crisis in Financial Research

27 Pages Posted: 11 May 2018 Last revised: 11 Dec 2018

See all articles by Marcos Lopez de Prado

Marcos Lopez de Prado

Cornell University - Operations Research & Industrial Engineering; True Positive Technologies

Date Written: May 11, 2018

Abstract

Most discoveries in empirical finance are false, as a consequence of selection bias under multiple testing. In this paper, we present a real example of how multiple testing information can be reported. We use that information to estimate the Deflated Sharpe Ratio of an investment strategy.

A presentation can be found at https://ssrn.com/abstract=3179826

Keywords: Backtest overfitting, selection bias, multiple testing, quantitative investments, machine learning, financial fraud, smart beta, factor investing.

JEL Classification: G0, G1, G2, G15, G24, E44

Suggested Citation

López de Prado, Marcos, A Data Science Solution to the Multiple-Testing Crisis in Financial Research (May 11, 2018). Available at SSRN: https://ssrn.com/abstract=3177057 or http://dx.doi.org/10.2139/ssrn.3177057

Marcos López de Prado (Contact Author)

Cornell University - Operations Research & Industrial Engineering ( email )

237 Rhodes Hall
Ithaca, NY 14853
United States

HOME PAGE: http://www.orie.cornell.edu

True Positive Technologies ( email )

NY
United States

HOME PAGE: http://www.truepositive.com

Register to save articles to
your library

Register

Paper statistics

Downloads
917
Abstract Views
3,038
rank
25,047
PlumX Metrics