The use of real-time data and technology has revolutionized the financial industry in the stocks and shares space, specifically in high-frequency trading. Now, improvements in data science promise to revamp the compliance space in a similar manner.
Tanvi Singh explores a case study illustrating how a very small data science team at a bank has approached the compliance world in a number-driven way. Tanvi highlights visual examples of metrics using Python summary plots where the entire bank risks are consolidated in a single plot. Such a scale factor allows metrics with completely different ranges—including anti-money laundering (AML), suitability and appropriateness (S&A), internal fraud (IF), and misconduct—to be shown on one chart. Using reference lines based on the risk appetite, these charts can flag current values between open and tight references, labeling suspicious activities yellow. If the values are flagged beyond the open reference, these very suspicious activities are coded red. This helps the ExB focus on key problems without making decisions based on approximation and has helped to match apples to oranges (a concept not attempted before). Tanvi offers various examples of such visualizations that can be applied in any domain.
Tanvi Singh is the Chief Analytics Officer, CCRO, at Credit Suisse. She leads a team of 60+ data scientists, data analysts, SME and Investigators globally in Zurich, New York, London, and Singapore. The team is delivering multimillion dollar projects in big data with leading Silicon Valley vendors in the space of RegTech. Tanvi has 18 years of experience in Data Science, business intelligence, Digital Analytics, Data platforms, Change and transformation with a focus on statistics, machine learning, text mining, and visualizations. Tanvi holds a master’s degree in software systems from the University of Zurich.
©2016, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.