Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910054809075712 |
|---|---|
| author | Sakhno, Artem Tomilov, Daniil Shakhvalieva, Yuliana Fedorova, Inessa Ruzanova, Daria Zoloev, Omar Savchenko, Andrey Makarenko, Maksim |
| author_facet | Sakhno, Artem Tomilov, Daniil Shakhvalieva, Yuliana Fedorova, Inessa Ruzanova, Daria Zoloev, Omar Savchenko, Andrey Makarenko, Maksim |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15459 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning Sakhno, Artem Tomilov, Daniil Shakhvalieva, Yuliana Fedorova, Inessa Ruzanova, Daria Zoloev, Omar Savchenko, Andrey Makarenko, Maksim Information Retrieval 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. |
| title | Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2603.15459 |