Corporate Bankruptcy Prediction with Domain-Adapted BERT

Alex Kim, Sangwon Yoon
12/6/2023
cs.CLcs.LGecon.GN

No official code found. Best implementation: AlexAcct/Bankrutpcy_BERT (4 stars, last commit 2022-04-21).

Abstract

This study performs BERT-based analysis, which is a representative contextualized language model, on corporate disclosure data to predict impending bankruptcies. Prior literature on bankruptcy prediction mainly focuses on developing more sophisticated prediction methodologies with financial variables. However, in our study, we focus on improving the quality of input dataset. Specifically, we employ BERT model to perform sentiment analysis on MD&A disclosures. We show that BERT outperforms dictionary-based predictions and Word2Vec-based predictions in terms of adjusted R-square in logistic regression, k-nearest neighbor (kNN-5), and linear kernel support vector machine (SVM). Further, instead of pre-training the BERT model from scratch, we apply self-learning with confidence-based filtering to corporate disclosure data (10-K). We achieve the accuracy rate of 91.56% and demonstrate that the domain adaptation procedure brings a significant improvement in prediction accuracy.

View on arXivView PDF

Code Implementations(1)

AlexAcct/Bankrutpcy_BERTCommunity58%

This code replicates "Corporate Bankruptcy Prediction with Domain-Adapted BERT" by Kim and Yoon (2021)

40PythonApr 21, 20224 years ago
bert

Similar Papers

Learning to Aggregate Zero-Shot LLM Agents for Corporate Disclosure Classification

83% match2026

A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges

82% match2024

Sentiment-driven prediction of financial returns: a Bayesian-enhanced FinBERT approach

82% match2024

Fine-Tuning Gemma-7B for Enhanced Sentiment Analysis of Financial News Headlines

82% match2024

Are Foundation Models Useful for Bankruptcy Prediction?

81% match2025

Financial Distress Prediction For Small And Medium Enterprises Using Machine Learning Techniques

81% match2023

Cite this paper

@article{kim2023corporate,
  title  = {Corporate Bankruptcy Prediction with Domain-Adapted BERT},
  author = {Alex Kim and Sangwon Yoon},
  year   = {2023},
  eprint = {2312.03194},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.03194v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.03194.svg)](https://codeofpaper.com/paper/2312.03194)

Discussion