Beyond the Black Box: An Intuitive Approach to Investment Prediction with Machine Learning

Posted: 5 Nov 2019

See all articles by Yimou Li

Yimou Li

State Street Associates

David Turkington

State Street Associates

Alireza Yazdani

State Street Associates

Date Written: October 23, 2019

Abstract

The complexity of machine learning models presents a substantial barrier to their adoption for many investors. The algorithms that generate machine learning predictions are sometimes regarded as “black box”, demanding interpretation and additional explanation. In this paper, we present a framework for demystifying the behavior of machine learning models and decomposing their predictions into linear, nonlinear, and interaction components. We also show how to decompose a model’s predictive efficacy into these same components. Together, this analysis forms a “model fingerprint” which we use to summarize its key characteristics and illustrate its similarities and differences compared to other models. We present a case study of this approach applying random forest, gradient boosting machine, and neural network models to the challenge of predicting monthly currency returns. We find that all three models reliably identify intuitive effects in the currency market, and that they also find new relationships attributable to nonlinearities and variable interactions. We argue that an understanding of these predictive components may help astute investors generate superior risk-adjusted returns.

Keywords: Interpretable Machine Learning, Foreign Exchange, Investment, Prediction, Neural Network, Random Forest, Gradient Boosting Machine

JEL Classification: C19, C40, C52, F31, G10, G11

Suggested Citation

Li, Yimou and Turkington, David and Yazdani, Alireza, Beyond the Black Box: An Intuitive Approach to Investment Prediction with Machine Learning (October 23, 2019). Available at SSRN: https://ssrn.com/abstract=3475538 or http://dx.doi.org/10.2139/ssrn.3475538

Yimou Li (Contact Author)

State Street Associates ( email )

140 Mt. Auburn St
Cambridge, MA 02138
United States

David Turkington

State Street Associates ( email )

United States

Alireza Yazdani

State Street Associates

140 Mount Auburn Street
Cambridge, MA 02138
United States

Register to save articles to
your library

Register

Paper statistics

Abstract Views
708
PlumX Metrics