The Serial Dependence of the Commodity Futures Returns: A Machine Learning Approach

53 Pages Posted: 8 Mar 2020 Last revised: 17 Aug 2020

See all articles by Yufeng Han

Yufeng Han

University of North Carolina (UNC) at Charlotte - Finance

Lingfei Kong

University of North Carolina at Charlotte

Date Written: January 11, 2020

Abstract

This paper uses machine learning tools to study the serial dependence (lead-lag relations) of commodity futures returns during the post financialization period (January 2004 – December 2019). We use LASSO (Least Absolute Shrinkage and Selection Operator) to select the predictors as the number of predictors is large relative to the number of observations. We find significant full-sample and out-of-sample predictability. In the full sample, we find that LASSO can identify a sparse set of predictors that come from economically linked commodities or are likely driven by excessive speculative trading. The out-of-sample forecasts based on the LASSO generate statistically and economically large gains. When we separate the indexed futures from the non-indexed futures and replicate the above analysis, we find that the out-of-sample performance exists in the indexed futures but disappears in the non-indexed futures. The lead-lag relations are also more significant after the advent of ETF or ETNs that track the broad futures indices such as S&P GSCI and BCOM indices, indicating that index trading due to financialization drives the excessive comovement among the commodity futures. Overall, we find that serial dependence generates significant predictability during the sample period when the performance of the long-only commodity index futures is poor.

Keywords: Commodity Futures, LASSO, Machine Learning, Predictability, Serial Dependence, Financialization, Comovement

JEL Classification: C22, C58, G11, G12, G14

Suggested Citation

Han, Yufeng and Kong, Lingfei, The Serial Dependence of the Commodity Futures Returns: A Machine Learning Approach (January 11, 2020). Available at SSRN: https://ssrn.com/abstract=3536046 or http://dx.doi.org/10.2139/ssrn.3536046

Yufeng Han (Contact Author)

University of North Carolina (UNC) at Charlotte - Finance ( email )

9201 University City Boulevard
Charlotte, NC 28223
United States

Lingfei Kong

University of North Carolina at Charlotte ( email )

9201 University City Blvd, Charlotte, NC 28223
Charlotte, NC 28262
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
86
Abstract Views
468
rank
324,254
PlumX Metrics