SAP的RPT-1模型在无训练数据下实现企业数据预测，表现接近传统机器学习。
Evaluating SAP RPT-1 for Enterprise Business Process Prediction: In-Context Learning vs. Traditional Machine Learning on Structured SAP Data
- 用预训练的RPT-1模型直接预测结构化企业数据，无需微调。
- 在2500~3200行数据上，分类准确率达梯度提升树的91-96%。
- 小样本（75-100行）时，RPT-1反而优于XGBoost，适合快速筛选。
表格基础模型旨在无需任务特定训练即可让企业数据应用机器学习。本文首次从实践者角度独立评估SAP的检索预训练变压器（RPT-1）。RPT-1是一个64.6 MB的紧凑模型，基于1.34 TB结构化数据（覆盖310万张表）预训练。我们在三个SAP业务场景中对比其与调优后的梯度提升决策树（XGBoost、LightGBM、CatBoost）的表现：跨SD/MM/PP模块的需求预测、BC/MM/QM中的预测数据完整性，以及FI/CO/AR中的财务风险分类。在2500至3200行数据的五折交叉验证中，RPT-1在无任何训练样本的情况下达到调优后GBDT 91%-96%的准确率。分类任务的差距较小，AUC-ROC仅差3.6-4.1个百分点；但回归任务差距较大，R²相差8.9-11.1个百分点。一个关键发现是，在约75-100个上下文样本时，RPT-1性能超越XGBoost。基于此，我们提出实用混合工作流：先用RPT-1快速筛查，再对精度要求高的场景选择性训练GBDT。所有实验均可通过公开的Hugging Face Spaces复现。
原文摘要 · Abstract (English)
Tabular foundation models aim to make machine learning accessible for enterprise data without task-specific training. This paper presents the first independent evaluation of SAP's Retrieval Pretrained Transformer (RPT-1) from a practitioner perspective. RPT-1 is a compact 64.6 MB model pretrained on 1.34 TB of structured data across 3.1 million tables. We benchmark it against tuned gradient-boosted decision trees (XGBoost, LightGBM, CatBoost) on three SAP business scenarios: demand forecasting across SD/MM/PP modules, predictive data integrity in BC/MM/QM, and financial risk classification in FI/CO/AR. Across five-fold cross-validation on datasets ranging from 2,500 to 3,200 rows, RPT-1 reaches 91-96% of tuned GBDT accuracy without any training examples. The classification gap is modest at 3.6-4.1 percentage points on AUC-ROC, though regression tasks show wider gaps of 8.9-11.1 percentage points on R-squared. An interesting finding is a crossover at roughly 75-100 context rows where RPT-1 actually outperforms XGBoost under limited data. Based on these results, we propose a practical hybrid workflow: use RPT-1 for rapid screening, then train GBDT selectively where prediction accuracy justifies the effort. All experiments are reproducible through publicly available Hugging Face Spaces.
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。