Autoregressive Random Forests: Machine Learning and Lag Selection for Financial Research

Computational Economics (https://doi.org/10.1007/s10614-023-10429-9)

42 Pages Posted: 1 Jun 2022 Last revised: 17 Aug 2023

See all articles by Efstathios Polyzos

Efstathios Polyzos

Zayed University

Costas Siriopoulos

Zayed University, College of Business; University of Patras - Business Administration

Date Written: May 24, 2022

Abstract

This paper demonstrates the use of Random Regression Forests (RRF) for optimal lag selection. Using an extended sample of 144 data series, of various data types with different frequencies and sample sizes, we perform optimal lag selection using RRF and compare the results with seven “traditional” information criteria as well as with three other machine learning approaches. We show that the different information criteria produce differing outcomes in terms of optimal lag selection. To quantify performance, we compare the forecast errors on autoregressive models using the optimal lags selected by the criteria and demonstrate that RRF outperforms other approaches. We provide suggestions to researchers as to which approach to use, under different combinations of data type/data frequency and data type/sample size.

Keywords: random regression forest, optimal lag, Lasso, Ridge regression, Bayesian model averaging

JEL Classification: C53, C13, C63, E52, E61, G17

Suggested Citation

Polyzos, Efstathios and Siriopoulos, Costas, Autoregressive Random Forests: Machine Learning and Lag Selection for Financial Research (May 24, 2022). Computational Economics (https://doi.org/10.1007/s10614-023-10429-9), Available at SSRN: https://ssrn.com/abstract=4118546 or http://dx.doi.org/10.2139/ssrn.4118546

Efstathios Polyzos (Contact Author)

Zayed University ( email )

Zayed University
P.O. Box 144534
Abu Dhabi
United Arab Emirates

Costas Siriopoulos

Zayed University, College of Business ( email )

P.O. Box 144534
Abu Dhabi
United Arab Emirates

University of Patras - Business Administration ( email )

Patras
Greece

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

Paper statistics

Downloads
227
Abstract Views
767
Rank
267,917
PlumX Metrics