Continual Learning Augmented Investment Decisions

TL;DR

This paper introduces Continual Learning Augmentation (CLA), a novel method combining explicit memory and neural networks to improve long-term investment decision accuracy with explainability, demonstrated through international equity simulations.

Contribution

The paper presents a new continual learning framework with empirically learned change points and dynamic time warping for memory recall, enhancing investment decision models.

Findings

CLA outperforms standard FFNN models in investment simulations.

Memory recall using DTW improves decision accuracy.

The approach offers explainable investment decision processes.

Abstract

Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which is based on an explicit memory structure and a feed forward neural network (FFNN) base model and used to drive long term financial investment decisions. We demonstrate that our approach improves accuracy in investment decision making while memory is addressed in an explainable way. Our approach introduces novel remember cues, consisting of empirically learned change points in the absolute error series of the FFNN. Memory recall is also novel, with contextual similarity assessed over time by sampling distances using dynamic time warping (DTW). We demonstrate the benefits of our approach by using it in an expected return forecasting task to drive investment decisions. In an investment simulation in a broad international equity universe between 2003-2017, our approach significantly outperforms FFNN base models. We also illustrate how CLA's memory addressing works in practice, using a worked example to demonstrate the explainability of our approach.