Interpretability in Safety-Critical FinancialTrading Systems

TL;DR

This paper introduces a gradient-based stress-testing method to evaluate how manipulations of inputs in ML-driven trading models can lead to significant negative impacts on return distributions, highlighting interpretability and robustness issues in financial systems.

Contribution

It presents a novel gradient-based approach for stress-testing trading models' robustness and interpretability in real-world financial pipelines, emphasizing end-to-end system performance.

Findings

Identifies input perturbations causing large negative return shifts

Demonstrates that forecast errors alone do not determine trading losses

Provides tools for interpreting ML forecasts in trading systems

Abstract

Sophisticated machine learning (ML) models to inform trading in the financial sector create problems of interpretability and risk management. Seemingly robust forecasting models may behave erroneously in out of distribution settings. In 2020, some of the world's most sophisticated quant hedge funds suffered losses as their ML models were first underhedged, and then overcompensated. We implement a gradient-based approach for precisely stress-testing how a trading model's forecasts can be manipulated, and their effects on downstream tasks at the trading execution level. We construct inputs -- whether in changes to sentiment or market variables -- that efficiently affect changes in the return distribution. In an industry-standard trading pipeline, we perturb model inputs for eight S&P 500 stocks. We find our approach discovers seemingly in-sample input settings that result in large negative shifts in return distributions. We provide the financial community with mechanisms to interpret ML forecasts in trading systems. For the security community, we provide a compelling application where studying ML robustness necessitates that one capture an end-to-end system's performance rather than study a ML model in isolation. Indeed, we show in our evaluation that errors in the forecasting model's predictions alone are not sufficient for trading decisions made based on these forecasts to yield a negative return.