Machine Learning Based Trading Strategies

26 Pages Posted: 25 Mar 2021

See all articles by Dilip B. Madan

Dilip B. Madan

University of Maryland - Robert H. Smith School of Business

Yazid Sharaiha

Norges Bank Investment Management (NBIM)

Date Written: October 8, 2019

Abstract

Dynamic contributions to trading are evaluated using covariations between position and price changes a horizon. Other performance measures like Sharpe ratios, Gain loss ratios, Acceptability indices and Drawdowns are also employed. Machine learning strategies based on Gaussian Process Regression (GPR) are compared with Least Squares (LSQ). Further both are generalized by invoking conservative valuation schemes that lead to the study of conservative conditional expectations modeled by distorted expectations. The latter lead to the development of distorted least squares (DLSQ) and distorted Gaussian Process Regression (DGPR) as the associated estimation or prediction schemes. Trading strategies are executed for nine sectors of the US economy using fourteen different predictive factor sets. Results support improvements made by GPR, DGPR over LSQ, DLSQ with the distorted versions also impacting favorably the drawdowns.

Keywords: Self Financing, Distorted Expectations, Active Portfolio Management, Zero covariation covariance

JEL Classification: G10, G12, G17

Suggested Citation

Madan, Dilip B. and Sharaiha, Yazid, Machine Learning Based Trading Strategies (October 8, 2019). Available at SSRN: https://ssrn.com/abstract=3782943 or http://dx.doi.org/10.2139/ssrn.3782943

Dilip B. Madan (Contact Author)

University of Maryland - Robert H. Smith School of Business ( email )

College Park, MD 20742-1815
United States
301-405-2127 (Phone)
301-314-9157 (Fax)

Yazid Sharaiha

Norges Bank Investment Management (NBIM) ( email )

Bankplassen 2
P.O. Box 1179 Sentrum
Oslo, NO-0107
Norway

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
198
Abstract Views
748
Rank
244,194
PlumX Metrics