Long-Term Modeling of Financial Machine Learning for Active Portfolio Management

TL;DR

This paper proposes a data augmentation method combining multiple time scales to improve long-term financial machine learning models, demonstrating its effectiveness in portfolio management across stock and FX markets.

Contribution

Introduces a novel data augmentation approach using multiple time scales to enhance long-term financial machine learning models for portfolio management.

Findings

Data augmentation improves model generalization for long-term tasks.

The method is effective in both stock and FX markets.

A versatile management model applicable across various financial markets.

Abstract

In the practical business of asset management by investment trusts and the like, the general practice is to manage over the medium to long term owing to the burden of operations and increase in transaction costs with the increase in turnover ratio. However, when machine learning is used to construct a management model, the number of learning data decreases with the increase in the long-term time scale; this causes a decline in the learning precision. Accordingly, in this study, data augmentation was applied by the combined use of not only the time scales of the target tasks but also the learning data of shorter term time scales, demonstrating that degradation of the generalization performance can be inhibited even if the target tasks of machine learning have long-term time scales. Moreover, as an illustration of how this data augmentation can be applied, we conducted portfolio management in which machine learning of a multifactor model was done by an autoencoder and mispricing was used from the estimated theoretical values. The effectiveness could be confirmed in not only the stock market but also the FX market, and a general-purpose management model could be constructed in various financial markets.