用图神经网络联合预测小企业13项财务指标，提升短期预测精度。
Accounting Graph Transformer for Short-History Multi-KPI Forecasting in Small Businesses
- 构建会计关系图，通过类型化注意力融合多科目信息。
- 在11993个未见公司上实现0.699的平均绝对误差，优于基线模型。
- 仅用530万参数模型即可跨公司通用预测，适合财务规划场景。
小企业通常仅有12-24个月的会计记录，但经营规划与风控需协同预测多个财务报表指标。本文研究从71个月度账目数据中联合预测13项损益表、资产负债表、现金流及营运资本关键绩效指标（KPIs），覆盖12个月期限。提出会计图变压器（AGT），将每个账目序列表示为掩码标记，通过固定会计关系图进行类型化注意力交互，聚合目标特定上下文，并融合门控的三个月近期路径。在1060家未见过公司的11,993个预测起点上，AGT实现样本加权的KPI宏观平均绝对误差（MAE）0.6990 ± 0.0013，优于最强基线LightGBM的0.7378 ± 0.0014。在指定种子42下，配对公司聚类自举检验显示，AGT相对于LightGBM的差异为0.0395，95%置信区间[0.0350, 0.0439]。在相同种子下，AGT在全部13个KPI上均优于LightGBM、TimeMixer和SOFTS；架构消融实验表明，关系注意力、会计拓扑结构及近期路径均显著提升验证与测试准确率。在另7,094家未见公司（预测起点取自2025年1-5月）上，AGT取得0.7548的MAE，优于SOFTS的0.7694。单个530万参数模型无需企业定制即可生成156个对齐预测，支持集成规划、流动性与营运资本分析。
原文摘要 · Abstract (English)
Small businesses often have only 12-24 months of accounting history, yet planning and risk workflows require coordinated forecasts across financial statements. We study joint 12-month forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators (KPIs) from 71 monthly ledger series. We introduce the Accounting Graph Transformer (AGT), which represents each ledger series as a masked token, exchanges information through typed attention on a fixed accounting-relation graph, pools target-specific context, and fuses it with a gated three-month recency path. Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-weighted KPI-macro mean absolute error (MAE) $0.6990 \pm 0.0013$ over three independent seeds, compared with $0.7378 \pm 0.0014$ for the strongest baseline, LightGBM. At the pre-specified seed 42, a paired company-clustered bootstrap gives a LightGBM-minus-AGT difference of 0.0395 with 95% confidence interval (CI) $[0.0350,0.0439]$. AGT is best on all 13 KPIs against LightGBM, TimeMixer, and SOFTS in the matched seed-42 comparison, while final-architecture ablations show that relational attention, accounting topology, and the recency path each improve validation and test accuracy. On 7,094 additional unseen companies with origins sampled from January-May 2025, AGT obtains 0.7548 MAE versus 0.7694 for SOFTS. A single 5.3M-parameter model produces 156 aligned forecasts without company-specific fitting, providing one forecasting layer for integrated planning, liquidity, and working-capital analysis.
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。