V4FinBench is a new million-record benchmark where imbalance-aware finetuned TabPFN matches or beats gradient boosting on long-horizon bankruptcy prediction while Llama-3-8B lags, with evidence of transferable patterns to US data.
Deep learning models for bankruptcy prediction using textual disclosures.European Journal of Operational Research, 274(2): 743–758
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A new dictionary-based text score from 10-K narratives adds incremental power to accounting-based bankruptcy prediction, lifting AUC by 0.07 and top-decile capture from 44% to 65% in holdout evaluation.
citing papers explorer
-
V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction
V4FinBench is a new million-record benchmark where imbalance-aware finetuned TabPFN matches or beats gradient boosting on long-horizon bankruptcy prediction while Llama-3-8B lags, with evidence of transferable patterns to US data.
-
Bankruptcy Prediction from 10-K Narratives: Evidence from Interpretable Text Scores and Accounting Baselines
A new dictionary-based text score from 10-K narratives adds incremental power to accounting-based bankruptcy prediction, lifting AUC by 0.07 and top-decile capture from 44% to 65% in holdout evaluation.