Reinforcement Learning for Financial Index Tracking

TL;DR

This paper introduces a novel discrete-time dynamic model for financial index tracking that incorporates intertemporal market dynamics, transaction costs, and cash management, solved with an extended deep reinforcement learning approach, demonstrating superior tracking and profit potential.

Contribution

It presents the first dynamic formulation for index tracking with intertemporal market variables and a new RL solution addressing data limitations, outperforming benchmarks.

Findings

Outperforms benchmark in tracking accuracy

Enables effective cash withdrawal strategies

Demonstrates potential for extra profit

Abstract

We propose the first discrete-time infinite-horizon dynamic formulation of the financial index tracking problem under both return-based tracking error and value-based tracking error. The formulation overcomes the limitations of existing models by incorporating the intertemporal dynamics of market information variables not limited to prices, allowing exact calculation of transaction costs, accounting for the tradeoff between overall tracking error and transaction costs, allowing effective use of data in a long time period, etc. The formulation also allows novel decision variables of cash injection or withdraw. We propose to solve the portfolio rebalancing equation using a Banach fixed point iteration, which allows to accurately calculate the transaction costs specified as nonlinear functions of trading volumes in practice. We propose an extension of deep reinforcement learning (RL) method to solve the dynamic formulation. Our RL method resolves the issue of data limitation resulting from the availability of a single sample path of financial data by a novel training scheme. A comprehensive empirical study based on a 17-year-long testing set demonstrates that the proposed method outperforms a benchmark method in terms of tracking accuracy and has the potential for earning extra profit through cash withdraw strategy.