THE SEARCH FOR TIME-SERIES PREDICTABILITY-BASED ANOMALIES

Ana Milena Padilla-Ospina,Javier Humberto Ospina-Holguín

doi:10.3846/jbem.2021.15650

Ana Milena Padilla-Ospina, Javier Humberto Ospina-Holguín

Open Access

https://doi.org/10.3846/jbem.2021.15650

Copy DOI

Abstract

This paper introduces a new algorithm for exploiting time-series predictability-based patterns to obtain an abnormal return, or alpha, with respect to a given benchmark asset pricing model. The algorithm proposes a deterministic daily market timing strategy that decides between being fully invested in a risky asset or in a risk-free asset, with the trading rule represented by a parametric perceptron. The optimal parameters are sought in-sample via differential evolution to directly maximize the alpha. Successively using two modern asset pricing models and two different portfolio weighting schemes, the algorithm was able to discover an undocumented anomaly in the United States stock market cross-section, both out-of-sample and using small transaction costs. The new algorithm represents a simple and flexible alternative to technical analysis and forecast-based trading rules, neither of which necessarily maximizes the alpha. This new algorithm was inspired by recent insights into representing reinforcement learning as evolutionary computation.

Highlights

This work introduces an algorithm designed to detect and profitably exploit the presence of time-series predictability-based anomalies
The rest of the paper is organized as follows: Section 1 provides a general overview of the literature associated with investment algorithms; Section 2 describes the algorithm for optimizing alpha directly and introduces the data used to test its efficacy; Section 3 provides the descriptive statistics of the data and the performance of the algorithm in terms of alphas for two types of size decile portfolios using two modern asset pricing models; the final section provides concluding remarks
It can be divided into four main branches: investment algorithms based on forecasts, investment algorithms based on conventional technical analysis, and investment algorithms based on reinforcement learning, which includes the fourth branch, algorithms based on policy optimization

Summary

Introduction

This work introduces an algorithm designed to detect and profitably exploit the presence of time-series predictability-based anomalies. This new approach was inspired by the work of Salimans, Ho, Chen, Sidor, and Sutskever (2017), which interpreted reinforcement learning as a general evolutionary algorithm form, broadly simplifying reinforcement learning programming Such simplification may enable advances in other financial fields (including risk management, portfolio allocation, and market microstructure) and in related economics fields (including stochastic games, real-time bidding, consumption and income dynamics, and adaptive experimental design) (cf Charpentier et al, 2021).. The time-series predictability-based anomaly is robust to changes in the benchmark asset-pricing model, from the Fama and French (2015) to the Carhart model (1997), and portfolio construction, from equal-weighted to value-weighted. The rest of the paper is organized as follows: Section 1 provides a general overview of the literature associated with investment algorithms; Section 2 describes the algorithm for optimizing alpha directly and introduces the data used to test its efficacy; Section 3 provides the descriptive statistics of the (out-of-sample) data and the performance of the algorithm in terms of alphas for two types of size decile portfolios using two modern asset pricing models; the final section provides concluding remarks

Literature review

Data and methodology

Results and discussion

Conclusions