Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning

TL;DR

FinTRACE is a retrieval-based architecture that transforms raw financial transactions into reusable features, significantly enhancing zero-shot and few-shot transaction analytics and enabling LLM grounding for improved financial reasoning.

Contribution

The paper introduces FinTRACE, a novel retrieval-first system for financial transaction analysis that improves low-supervision performance and enhances LLM grounding in financial contexts.

Findings

Doubling zero-shot MCC on churn prediction from 0.19 to 0.38

Improving 16-shot MCC from 0.25 to 0.40

Achieving state-of-the-art LLM results on transaction analytics

Abstract

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.