Christos Boutsidis is the Vice President of the Relationship Analytics and Engineering Department at Goldman Sachs. The focus of his organization is on building the Goldman Sachs Knowledge Graph and making it available firm-wide. Towards that end, they combine multiple sources of structured (e.g., trades, transactions) and unstructured (e.g., text, voice) data into a single, highly heterogeneous, knowledge graph with hundreds of millions of nodes and billions of edges - their mission is to capture all the firm relationships related to communication, trading, as well as money transfers. From an algorithms perspective, the team develops scalable solutions (Hadoop, MapReduce, HDFS, HBase) for several graph mining problems such as vertex centrality (e.g., pagerank), vertex similarity, (shortest) paths, vertex deduplication, community detection, and graph embeddings, to name a few. From an applications point of view, their work is used 1) within the Compliance Division, to enable the development of regulatory surveillances such as detection of insider trading and anti money laundering 2) outside of the Compliance Division, in particular, in the “One Goldman Sachs” initiative, a cross-divisional client coverage initiative that will develop and implement a more integrated approach to serving the firm’s clients who interact with multiple divisions, including Securities, Investment Banking, Investment Management, and Merchant Banking.   Before that, Christos was a Research Scientist with the Scalable Machine Learning Group of Yahoo Research in New York and a Research Staff Member with the 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 from the University of Patras, in Greece in July of 2006. Dr Boutsidis has published over 30 articles in conferences and journals in algorithms, machine learning, and statistical data analysis.  

2020 Talk: Towards building a CRM system using a Knowledge Graph of Communication Data

In this talk, I will describe the challenges of building a Client Relationship Management (CRM) system automatically starting from the electronic communication (e.g., email) data between a firm and its clients. Building a communication Knowledge Graph from emails is the starting point in such a design of a CRM system - several other complex technical graph algorithmic problems follow: vertex centrality (aka client importance), edge strength (aka client coverage), vertex deduplication (aka unique client identification). Putting everything together, this talk tells the story of how crm-related business questions posed by bankers turn into technical problems solved by engineers, leading to the design of a CRM system whose users don’t maintain manually, yet enjoy using it.  

2019 Talk: Pythia: the Goldman Sachs Social Graph

  Pythia is a social network built to capture communication, trading, as well as financial transactions activities within Goldman Sachs. It consists of around 100 M vertices and 2 B edges. We had built Pythia using first-order engineering principles such as hadoop/mapreduce/hbase/java/protocol buffers. In this talk, I will describe Pythia, few engineering aspects of our work, and how it is used within the firm.