用Transformer预测未来20个季度财务报表，精度随时间提升且保持会计一致性。
Long-Horizon Forecasting of Complete Financial Statements with Forma
- 将财务表项视为(科目, 季度, 数值)元组，用掩码元组高斯似然训练
- 在1-20个季度预测上超越所有对手，长期预测误差更小
- 支持无需重训的场景分析，适合投资估值与风险评估者
现有研究未实现超过一年的完整财务报表联合预测，而折现现金流估值中大部分企业价值来自该时间窗口之外。我们发布ProForma-20Q，一个可复现的基准，用于从过往报表和行业代码出发，预测78个报表项目1至20个季度后的数值，采用变化空间$R^2$评分。Forma模型以变换器读取(账户, 季度, 值)元组，最大化掩码元组高斯似然，在该基准上击败所有对比方法：传统机器学习、链式梯度提升、零样本时间序列基础模型及前沿大语言模型。其优势随预测周期拉长而扩大，正是估值最需准确的时段；其高斯预测区间从未低估实际值。预报结果近乎满足会计恒等式，精确一致性恢复无显著精度损失。其元组接口支持无需重训的场景分析，我们证明固定未来收入路径可显著提升其他项目预测精度。
原文摘要 · Abstract (English)
Specialist training beats generalist scale when forecasting financial statements. To our knowledge, no prior work jointly forecasts complete financial statements beyond one year, yet in a discounted-cash-flow valuation most firm value sits past that window. We release ProForma-20Q, a reproducible benchmark for forecasting 78 statement line items 1-20 quarters ahead, for anonymized firms, from past statements and an industry code, scored by change-space $R^2$. On it, Forma, a transformer that reads statements as sets of (account, quarter, value) tuples and maximizes a masked-tuple Gaussian likelihood, beats every competitor we field: classical machine learning, chained gradient boosting, a zero-shot time-series foundation model, and frontier large language models. Its lead widens with horizon, where valuation needs accuracy most, and its Gaussian predictive intervals never under-cover. Forma's forecasts nearly satisfy accounting identities; exact coherence is recoverable at no statistically significant accuracy cost. Its tuple interface supports scenario analysis without retraining, and we show that pinning future revenue paths sharpens the rest of the statement.
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。