Graph Analytics for Bank Compliance

Friday, November 3, 2017 - 1:25pm - 2:25pm
Lind 305
Christos Boutsidis (Goldman Sachs)
We describe communication and trading connections between bank employees and clients. We analyze these connections with a large graph (100M vertices, 2B edges). After discussing some challenges in scaling algorithms to deal with this graph (for example pagerank), we outline applications in compliance surveillance; these include detecting insider trading activity, and building a compliance search engine.

CHRISTOS BOUTSIDIS is with the Surveillance Analytics Group of Goldman Sachs, where his focus is on designing and implementing algorithms for compliance surveillances. Before that, he was a Research Scientist with the Scalable Machine Learning Group of Yahoo Research in New York and a Research Staff Member with the Business Analytics and Mathematical Sciences Department of the IBM T. J. Watson Research Center in Yorktown Heights, NY. Dr. Boutsidis earned a Ph.D. in Computer Science from Rensselaer Polytechnic Institute in May of 2011 and a BS in Computer Engineering and Informatics from the University of Patras, in Greece in July of 2006. Dr Boutsidis's research interests lie in the design and analysis of fast approximation algorithms for matrix computations and applications of those to machine learning and data analysis problems. Dr. Boutsidis has published over 30 articles in conferences and journals in numerical linear algebra, theoretical computer science, and statistical data analysis.