[Back]

L. Bellomarini, E. Laurenza, E. Sallinger:
"Rule-based Anti-Money Laundering in Financial Intelligence Units: Experience and Vision";
Talk: RuleML+RR 2020 - 4th International Joint Conference on Rules and Reasoning, Oslo, Norway; 2020-06-29 - 2020-07-01; in: "Proceedings of the 14th International Rule Challenge, 4th Doctoral Consortium, and 6th Industry Track @ RuleML+RR 2020 co-located with 16th Reasoning Web Summer School {(RW} 2020) 12th DecisionCAMP 2020 as part of Declarative {AI} 2020, Oslo, Norway (virtual due to Covid-19 pandemic), 29 June - 1 July, 2020", (2020), 133 - 144.

Money laundering is a major threat to the good functioning of finan-cial systems. Despite huge technological investments, with machine learning atthe heart of the Fintech revolution, we are still lacking explainable solutions infighting money laundering, especially for Financial Intelligence Units (FIUs).This paper is based on the joint committment of the Fintech community andacademia in applying state-of-the-art rule-based reasoning to counteract moneylaundering. We report a visionary position about the application of logic-basedKnowledge Graphs and reasoning with languages in the Datalog+/- family in theanti-money laundering (AML) domain. After motivating the impact and the im-portance of an explainable rule-based solution, we pin down the core AML prob-lems in the form of high-level decision tasks. We envision that the FIU knowledgeis modeled as the ground truth of a KG, so that AML tasks are formulated andcarried out as reasoning tasks, addressing specific quality desiderata. We providetechnical zoom and concrete exemplification of the approach with a real moneylaundering case. We discuss relevant research and technological challenges.

Project Head Reinhard Pichler:
KnowledgeGraph