From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale

2026-09-17

AI Summary

论文提出一种基于交易模式而非用户个体的语义用户画像方法，通过解析、推断和标签三个阶段构建可查询数据库，大幅减少大规模应用中的推理成本。

Abstract

Per-user LLM inference on transaction histories binds the inference budget linearly to user count, which becomes prohibitive at applied scale. We re-cast attribute inference from per-user to per-transaction-pattern. The pipeline runs in three phases: Resolve abstracts item names with optional web grounding, Profile infers attributes for each frequent pattern, and Tag clusters free-text attributes into a queryable database. In Profile, a single LLM call per pattern emits predefined categorical labels, free-text attributes, and per-attribute prevalence estimates. Because inference runs over patterns rather than users, the budget grows with the pattern count rather than the user count. On the public Open e-commerce corpus, the database is statistically indistinguishable from an LLM that reads each user's raw history directly in AUC across the evaluated attributes, and the prevalence estimates carry discriminative signal between positive and negative users. The pipeline is deployed at a major Japanese bank profiling on the order of tens of millions of users, with close to a three-order-of-magnitude reduction in LLM inference targets versus a per-user pipeline. The code is publicly available on https://github.com/CyberAgentAILab/profiling-agent-open-ecommerce.

Problem

• semantic user profiling
• transaction history
• inference budget
• large language model
• attribute inference

Innovation

• per-transaction-pattern
• attribute inference
• LLM budget reduction
• semantic user profiling