用检索式架构提升金融交易分析，让大模型更懂用户行为。
Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
- 先检索后建模，将交易数据转为可复用的行为特征。
- 零样本下流失预测的MCC从0.19提升至0.38，16样本提升至0.40。
- 适合金融风控、用户画像等低监督场景的智能分析。
当前金融机构的成功高度依赖于对客户数字痕迹（如交易历史）的处理能力，这些数据来自多个来源，用于优化用户建模流程。由于通用大模型难以处理时间分布的表格数据，生产系统仍依赖专用的表格和序列模型，存在泛化性差且需大量标注数据的问题。为此，我们提出FinTRACE，一种以检索为核心的架构：将原始交易转换为可复用的特征表示，通过规则检测器生成信号，并存入带有任务关联度的行为知识库。在公开与工业基准上，FinTRACE显著提升低监督交易分析性能，零样本下流失预测的马修相关系数（MCC）从0.19提升至0.38，16样本下从0.25提升至0.40。此外，我们利用检索到的行为模式对大模型进行指令微调，使其在交易分析任务中达到当前最优表现。
原文摘要 · Abstract (English)
Nowadays, success of financial organizations heavily depends on their ability to process digital traces generated by their clients, e.g., transaction histories, gathered from various sources to improve user modeling pipelines. As general-purpose LLMs struggle with time-distributed tabular data, production stacks still depend on specialized tabular and sequence models with limited transferability and need for labeled data. To address this, we introduce FinTRACE, a retrieval-first architecture that converts raw transactions into reusable feature representations, applies rule-based detectors, and stores the resulting signals in a behavioral knowledge base with graded associations to the objectives of downstream tasks. Across public and industrial benchmarks, FinTRACE substantially improves low-supervision transaction analytics, doubling zero-shot MCC on churn prediction performance from 0.19 to 0.38 and improving 16-shot MCC from 0.25 to 0.40. We further use FinTRACE to ground LLMs via instruction tuning on retrieved behavioral patterns, achieving state-of-the-art LLM results on transaction analytics problems.
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。