构建百万级企业破产预测数据集，评估模型在真实金融场景下的表现
V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction
- 构建涵盖100万条公司年度记录的V4FinBench数据集，支持多时序预测
- 微调后的TabPFN在长周期预测中超越梯度提升模型，而LLaMA-3表现较弱
- 适用于金融风险建模、表格基础模型评估的研究者与从业者
企业破产预测是高风险金融任务，面临严重类别不平衡和多时序预测需求。现有公开数据集规模小且稀缺：常用免费基准包含6,000至80,000条公司年度记录，更大资源需付费订阅。为填补此空白，我们提出V4FinBench，一个涵盖维斯格拉德集团（V4）经济体2006–2021年超过一百万条公司年度记录的基准数据集，包含131个财务与非财务特征、六个预测时距，以及综合反映偿付能力、盈利性和流动性恶化的复合危机标准。该数据集设计用于在真实类别不平衡条件下评估表格模型与基础模型，正类率介于0.19%至0.36%之间。我们提供了标准表格基线、微调版TabPFN及QLoRA微调版Llama-3-8B的参考评估。采用不平衡感知微调后，TabPFN在长时距上$F_1$得分和ROC-AUC均匹配或超越梯度提升模型；相比之下，Llama-3-8B在所有时距的ROC-AUC均落后于梯度提升模型，且$F_1$得分普遍较低，长期差距显著扩大。在外部美国破产数据集上的评估显示，基于V4FinBench微调的TabPFN性能优于原始版本，表明其捕捉到可迁移的财务危机结构而非仅限于V4特定模式。V4FinBench已公开发布，以支持更真实的金融预测方法评估与发展。
原文摘要 · Abstract (English)
Corporate bankruptcy prediction is a high-stakes financial task characterized by severe class imbalance and multi-horizon forecasting demands. Public datasets supporting it remain scarce and small: widely used free benchmarks contain between 6,000 and 80,000 company-year observations, while larger resources are behind subscription paywalls. To address this gap, we introduce V4FinBench, a benchmark of over one million company-year records from the Visegràd Group (V4) economies (2006-2021), with 131 financial and non-financial features, six prediction horizons, and a composite distress criterion jointly capturing solvency, profitability, and liquidity deterioration. V4FinBench is designed to support the evaluation of tabular and foundation-model methods under realistic class imbalance, with positive rates between 0.19% and 0.36%. We provide reference evaluations of standard tabular baselines, finetuned TabPFN, and QLoRA-finetuned Llama-3-8B. With imbalance-aware finetuning, TabPFN matches or exceeds gradient boosting at longer time horizons on both $F_1$-score and ROC-AUC. In contrast, Llama-3-8B trails gradient boosting on ROC-AUC at every horizon and is generally weaker on $F_1$-score, with the gap widening sharply beyond the immediate horizon. In an external evaluation on the American Bankruptcy Dataset, the V4FinBench-finetuned TabPFN checkpoint improves over vanilla TabPFN, suggesting that adaptation captures transferable financial-distress structure rather than only V4-specific patterns. V4FinBench is publicly released to support further evaluation and development of prediction methods on realistic financial data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。