Explainable AI for Comprehensive Risk Assessment for Financial Reports: A Lightweight Hierarchical Transformer Network Approach

TL;DR

This paper introduces TinyXRA, a lightweight, explainable transformer model that enhances financial risk assessment from 10-K reports by incorporating comprehensive risk metrics and providing intuitive visual explanations, achieving state-of-the-art accuracy.

Contribution

The paper presents TinyXRA, a novel, scalable, and interpretable transformer-based model that integrates multiple risk measures and a dynamic visualization mechanism for improved financial risk analysis.

Findings

Achieves state-of-the-art accuracy across seven years of data.

Provides transparent risk explanations through attention-based visualizations.

Outperforms existing methods using triplet loss for risk classification.

Abstract

Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk. We propose Tiny eXplainable Risk Assessor (TinyXRA), a lightweight and explainable transformer-based model that automatically assesses company risk from these reports. Unlike prior work that relies solely on the standard deviation of excess returns (adjusted for the Fama-French model), which indiscriminately penalizes both upside and downside risk, TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment. We leverage TinyBERT as our encoder to efficiently process lengthy financial documents, coupled with a novel dynamic, attention-based word cloud mechanism that provides intuitive risk visualization while filtering irrelevant terms. This lightweight design ensures scalable deployment across diverse computing environments with real-time processing capabilities for thousands of financial documents which is essential for production systems with constrained computational resources. We employ triplet loss for risk quartile classification, improving over pairwise loss approaches in existing literature by capturing both the direction and magnitude of risk differences. Our TinyXRA achieves state-of-the-art predictive accuracy across seven test years on a dataset spanning 2013-2024, while providing transparent and interpretable risk assessments. We conduct comprehensive ablation studies to evaluate our contributions and assess model explanations both quantitatively by systematically removing highly attended words and sentences, and qualitatively by examining explanation coherence. The paper concludes with findings, practical implications, limitations, and future research directions. Our code is available at https://github.com/Chen-XueWen/TinyXRA.