Paper: arXiv 2405.01881
Authors: Xue Wen Tan, Stanley Kok
Abstract
Every publicly traded company in the US is required to file an annual 10-K financial report, which contains a wealth of information about the company. In this paper, we propose an explainable deep-learning model, called FinBERT-XRC, that takes a 10-K report as input, and automatically assesses the post-event return volatility risk of its associated company. In contrast to previous systems, our proposed model simultaneously offers explanations of its classification decision at three different levels: the word, sentence, and corpus levels. By doing so, our model provides a comprehensive interpretation of its prediction to end users. This is particularly important in financial domains, where the transparency and accountability of algorithmic predictions play a vital role in their application to decision-making processes. Aside from its novel interpretability, our model surpasses the state of the art in predictive accuracy in experiments on a large real-world dataset of 10-K reports spanning six years.
Complexity vs Empirical Score
- Math Complexity: 3.5/10
- Empirical Rigor: 7.5/10
- Quadrant: Street Traders — practical and empirical, lighter on theory
Why this score: The paper introduces FinBERT-XRC, a strong applied deep learning framework targeting multi-level explainability for 10-K risk classification. While mathematical formulations are relatively standard for NLP Transformer architectures, the empirical validation over a six-year multi-company dataset provides robust practical value.
Research Flowchart
flowchart TD
A["Research Goal: Explainable & Accurate Financial Risk Assessment"] --> B["Input Data: 6 Years of Publicly Traded 10-K Reports"]
B --> C["Model Architecture: FinBERT-XRC Deep Learning"]
C --> D["Risk Prediction: Post-Event Return Volatility Risk"]
C --> E["Multi-Level XAI Generation: Word, Sentence & Corpus Levels"]
D --> F["Outcomes: Superior Accuracy vs SOTA & Transparent Multi-Level Interpretability"]
E --> F