Exploring the Factor Zoo With a Machine-Learning Portfolio

49 Pages Posted: 9 Aug 2018 Last revised: 4 Sep 2019

See all articles by Halis Sak

Halis Sak

Hong Kong University of Science & Technology (HKUST) - Department of Finance

Tao Huang

Beijing Normal University-Hong Kong Baptist University United International College

Michael Chng

Xian Jiaotong Liverpool University; Department of Finance, Deakin University

Date Written: June 24, 2018

Abstract

Over the years, top journals have published a factor zoo containing hundreds of characteristics, only to see many of them losing empirical significance over time. In this paper, we perform an out-of-sample factor-zoo analysis on the rise and fall of characteristics in explaining cross-sectional stock return. To achieve this, we train different machine-learning (ML) models on 106 firm and trading characteristics to generate factor structures that relate characteristics to stock return. Using the combined forecast from ML models, we form a ML portfolio in predicted winner and loser stocks, over 18 years. The ML alpha is highly significant against all entrenched factor models, as well as a 'zoo-factor' that combines the ML portfolio's dominant characteristics using the Stambaugh and Yuan (2017) mispricing factor approach. Although the ML models are trained on the factor zoo, the ML portfolio's dominant characteristics revolve around just 10 features. Furthermore, we uncover a rotation pattern between a subset of features that proxy for arbitrage constraint on investors, and another that proxy for financial constraint on firms. Our paper provides an insight on how characteristics fundamentally explain stock returns over time.

Keywords: Machine Learning, Characteristics, Return Predictability, Portfolio Evaluation

JEL Classification: G12, G32

Suggested Citation

Sak, Halis and Huang, Tao and Chng, Michael, Exploring the Factor Zoo With a Machine-Learning Portfolio (June 24, 2018). WRDS Research Paper. Available at SSRN: https://ssrn.com/abstract=3202277 or http://dx.doi.org/10.2139/ssrn.3202277

Halis Sak (Contact Author)

Hong Kong University of Science & Technology (HKUST) - Department of Finance ( email )

Clear Water Bay, Kowloon
Hong Kong

Tao Huang

Beijing Normal University-Hong Kong Baptist University United International College ( email )

2000 Jintong Road
Zhuhai, Guangdong 519087
China

Michael Chng

Xian Jiaotong Liverpool University ( email )

BB520, 111 Ren Ai Lu
Higher Education Zone, SIP
Suzhou, Jiangsu 215123
China

Department of Finance, Deakin University ( email )

75 Pigdons Road
Victoria, Victoria 3216
Australia

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
323
Abstract Views
1,528
rank
99,935
PlumX Metrics