Paper
Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
Authors
Artem Sakhno, Daniil Tomilov, Yuliana Shakhvalieva, Inessa Fedorova, Daria Ruzanova, Omar Zoloev, Andrey Savchenko, Maksim Makarenko
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.15459v1</id>\n <title>Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning</title>\n <updated>2026-03-16T15:56:21Z</updated>\n <link href='https://arxiv.org/abs/2603.15459v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.15459v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n <published>2026-03-16T15:56:21Z</published>\n <arxiv:primary_category term='cs.IR'/>\n <author>\n <name>Artem Sakhno</name>\n </author>\n <author>\n <name>Daniil Tomilov</name>\n </author>\n <author>\n <name>Yuliana Shakhvalieva</name>\n </author>\n <author>\n <name>Inessa Fedorova</name>\n </author>\n <author>\n <name>Daria Ruzanova</name>\n </author>\n <author>\n <name>Omar Zoloev</name>\n </author>\n <author>\n <name>Andrey Savchenko</name>\n </author>\n <author>\n <name>Maksim Makarenko</name>\n </author>\n </entry>"
}