Commodity Risk Factors: A Machine Learning Approach

53 Pages Posted:

See all articles by Clemens C. Struck

Clemens C. Struck

University College Dublin

Enoch Cheng

University of Colorado at Denver - Department of Economics

Date Written: June 27, 2019

Abstract

To which extent are financial market returns predictable? Standard linear approaches à la Fama & French (1992) are widespread. Yet, they have difficulties in addressing this question as implicit assumptions undermine their return predicting potential. We employ tree-based methods to overcome these limitations and attempt to empirically approximate an upper bound for the predictability of commodities futures returns. Out-of-sample, we find that up to 3.74% of one-month ahead returns are predictable --- more than a 10-fold increase from linear risk factor approaches. Our findings hint at the importance multi-way interactions and non-linearities acquire in the data. They imply that new factors should be tested on their ability to add explanatory power to an ensemble of existing factors.

Keywords: Machine Learning, Empirical Asset Pricing, Ensemble Methods, Return Forecasting

JEL Classification: G11, G12, G13, G14

Suggested Citation

Struck, Clemens and Cheng, Enoch, Commodity Risk Factors: A Machine Learning Approach (June 27, 2019). Available at SSRN: https://ssrn.com/abstract=

Clemens Struck (Contact Author)

University College Dublin ( email )

School of Economics
Belfield, Dublin 4
Ireland

HOME PAGE: http://ccstruck.weebly.com

Enoch Cheng

University of Colorado at Denver - Department of Economics ( email )

Campus Box 181
P.O. Box 173364
Denver, CO 80217-3364
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
1,953
Abstract Views
6,867
PlumX Metrics