Measuring Consistency in Text-based Financial Forecasting Models

TL;DR

This paper introduces FinTrust, a tool to evaluate the logical consistency of NLP models in financial forecasting, revealing that current models lack robustness under meaning-preserving input variations.

Contribution

The paper presents FinTrust, the first evaluation framework for assessing consistency in text-based financial forecasting models, highlighting their poor robustness.

Findings

State-of-the-art models show low consistency in financial text predictions.

Meaning-preserving input changes significantly degrade model performance.

Current NLP methods are inadequate for reliable financial forecasting.

Abstract

Financial forecasting has been an important and active area of machine learning research, as even the most modest advantage in predictive accuracy can be parlayed into significant financial gains. Recent advances in natural language processing (NLP) bring the opportunity to leverage textual data, such as earnings reports of publicly traded companies, to predict the return rate for an asset. However, when dealing with such a sensitive task, the consistency of models -- their invariance under meaning-preserving alternations in input -- is a crucial property for building user trust. Despite this, current financial forecasting methods do not consider consistency. To address this problem, we propose FinTrust, an evaluation tool that assesses logical consistency in financial text. Using FinTrust, we show that the consistency of state-of-the-art NLP models for financial forecasting is poor. Our analysis of the performance degradation caused by meaning-preserving alternations suggests that current text-based methods are not suitable for robustly predicting market information. All resources are available at https://github.com/yingpengma/fintrust.