Abstract
Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose CallMine, with carefully designed features and visualizations. Our CallMine method has the following properties: (a) Scalable, being linear on the input size, handling about 35 million records in around one hour on a stock laptop; (b) Effective, allowing natural interaction with human analysts; (c) Flexible, being applicable in both supervised and unsupervised settings; (d) Automatic, requiring no user-defined parameters. In the real world, in a multi-million-scale dataset, CallMine was able to detect fraudsters 7,000x faster, namely in a matter of hours, while expert humans took over 10 months to detect them. CIKM-ARP Categories: Application; Analytics and machine learning; Data presentation.
Funding Information
  • Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR) and the Army Research Office (ARO) (FA9550-21-F-0003)
  • Portuguese Foundation for Science and Technology - FCT under CMU Portugal
  • São Paulo Research Foundation - FAPESP (2021/11403-5, 2020/11258-2, 2016/17078-0, 2020/07200-9)
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) (001)
  • AIDA project - Adaptive, Intelligent and Distributed Assurance Platform (POCI-01-0247-FEDER-045907)
  • National Science Foundation Graduate Research (DGE1745016, DGE2140739)
  • Pennsylvania Infrastructure Technology Alliance - PITA award
  • European Regional Development Fund - ERDF through the Operational Program for Competitiveness and Internationalisation - COMPETE 2020
  • National Council for Scientific and Technological Development (CNPq)