News & Success Stories
Tremend, in partnership with the University Politehnica of Bucharest and the University of Bucharest, started a research project for developing Graphomaly, an AI-based solution for detecting anomalies in patterns of financial transactions.
Born out of the need to tackle the increase of fraudulent transactions across the European space, this advanced Python software package will automatically discover illicit behavior like money laundering, illegal networks, tax evasion, and scams.
The Graphomaly toolbox will use financial data models evaluated as individual data points, graphs, or time series, for anomaly detection. Given a large dataset of transactions, this toolbox will be able to produce the subset of anomalous data in the following basic scenarios:
- Starting from known patterns, modeling and analyzing sub-graphs through community detection;
- Finding new, unseen patterns, in an unsupervised/semi-supervised manner.
Graphomaly uses AI algorithms and automated procedures to save time and money for companies and banks. This new tool will be able to process large graphs, so that reaction time is decreased and, thus, frauds can be discovered in their incipient stages.
The project is aligned with Tremend’s general strategy and focuses on research and innovation, in Artificial Intelligence and Machine Learning, within the financial services industry.
This work was supported by a grant from the Romanian Ministry of Education and Research, UEFISCDI, PNCDI III (Programme 2), and CCCDI (Subprogramme 2.1). Project registration code: PN-III-P2-2.1-PED-2019-3248, Project title: Graphomaly – a software package for anomaly detection in graphs modeling financial transactions.