Towards AI Analyst: Querying Costly Features for Fraud and Money Laundering Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00388386" target="_blank" >RIV/68407700:21230/25:00388386 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/COMPSAC65507.2025.00262" target="_blank" >https://doi.org/10.1109/COMPSAC65507.2025.00262</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/COMPSAC65507.2025.00262" target="_blank" >10.1109/COMPSAC65507.2025.00262</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards AI Analyst: Querying Costly Features for Fraud and Money Laundering Detection

Popis výsledku v původním jazyce

Fraud and money laundering detection in financial transaction data is a highly regulated field where explanations and human decisions are paramount to deploying any automatic detection models. Artificial intelligence (AI) methods are already routinely used for the detection of suspicious transactions, but their application in the final stage of analysis is underexplored. To assess the prospects for AI in this task, we analyze the work of a human analyst as a data processing agent. Specifically, we analyze textual feedback from real human analysts to determine the focus of their work and identify how AI can improve it. We conclude that analysts do not spend their time reanalyzing or explaining the raw transaction data but actively seek additional information. This paradigm is formalized in machine learning as learning with costly features. We applied state-of-the-art methods to studied data and concluded that using the costly features paradigm leads to an optimal trade-off between the cost of the feature acquisition and model performance. We believe that this approach is ready to be applied in the production stage. We provide a full code of our approach as well as a modification of publicly available data to reproduce our results.

Název v anglickém jazyce

Towards AI Analyst: Querying Costly Features for Fraud and Money Laundering Detection

Popis výsledku anglicky

Fraud and money laundering detection in financial transaction data is a highly regulated field where explanations and human decisions are paramount to deploying any automatic detection models. Artificial intelligence (AI) methods are already routinely used for the detection of suspicious transactions, but their application in the final stage of analysis is underexplored. To assess the prospects for AI in this task, we analyze the work of a human analyst as a data processing agent. Specifically, we analyze textual feedback from real human analysts to determine the focus of their work and identify how AI can improve it. We conclude that analysts do not spend their time reanalyzing or explaining the raw transaction data but actively seek additional information. This paradigm is formalized in machine learning as learning with costly features. We applied state-of-the-art methods to studied data and concluded that using the costly features paradigm leads to an optimal trade-off between the cost of the feature acquisition and model performance. We believe that this approach is ready to be applied in the production stage. We provide a full code of our approach as well as a modification of publicly available data to reproduce our results.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-32620S" target="_blank" >GA22-32620S: Učení bez učitele nad heterogenními strukturovanými daty</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC)

ISBN

979-8-3315-7435-2

ISSN

2836-3787

e-ISSN

2836-3795

Počet stran výsledku

6

Strana od-do

1905-1910

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Toronto

Datum konání akce

8. 7. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001575960000253