Anti-Money Laundering - Ashrith Barthur, Security Scientist, H2O.ai
Presented at #H2OWorld 2017 in Mountain View, CA. Enjoy the video: https://youtu.be/1ujtVBimH8Y. Learn more about H2O.ai: https://www.h2o.ai/. Follow @h2oai: https://twitter.com/h2oai. - - - Abstract: In this talk, Ashrith will be introducing you to the idea of using machine learning for detecting money laundering. The idea behind using ML for detecting money laundering is that the current rules-based engine have limited visibility into money movement. And as models learn the nuances of money movement, especially illegal, much better money laundering detection is possible. Ashrith's Bio: Ashrith is the security scientist designing anomalous detection algorithms at H2O.ai. He recently graduated from the Center of Education and Research in Information Assurance and Security (CERIAS) at Purdue University with a PhD in Information security. He is specialized in anomaly detection on networks under the guidance of Dr. William S. Cleveland. He tries to break into anything that has an operating system, sometimes into things that don’t. He has been christened as “The Only Human Network Packet Sniffer” by his advisors. When he is not working, he swims and bikes long distances.
Recommended
Recommended
More Related Content
Similar to Anti-Money Laundering - Ashrith Barthur, Security Scientist, H2O.ai
Similar to Anti-Money Laundering - Ashrith Barthur, Security Scientist, H2O.ai (20)
More from Sri Ambati
More from Sri Ambati (20)
Recently uploaded
Recently uploaded (20)
Anti-Money Laundering - Ashrith Barthur, Security Scientist, H2O.ai
- 4. What is Money Laundering?
- 6. Sources of Illegal Money Unrecorded Sources of Income Human Trafficking Source: anandnimesh.com, texasrightolife.com, newsofthesouth.com.
- 7. How does it affect us (society) ? Source: @ThepuppetGovt, europeanreform.org, daurr.com
- 8. How do we catch it now?
- 9. What are the Limitation? 1.Rule Systems are purely based on previously seen behaviour. 2.The rule systems are deterministic. 3. The security analyst has only finite time.
- 10. …therefore, what is the Problem? 1.More money, faster transactions, lots of transactions in a connected world. 2.Creative ways of committing money laundering. 3.Too many rules. 4.Lots of cases to process for analysts.
- 11. What is the Solution? Source: Kdnuggets.com, wikimedia.org,
- 12. What is Needed? Source: Kdnuggets.com, wikimedia.org, 1.Data – exhaustive, quality data. 2.Features – quality features that capture the nuances in the data.
- 14. Is this Future Proof? Source: ledvision.com.my Can I capture newer and creative ways of money laundering?
- 15. Anomalous Behaviour Source: 1000waystopray.com 1. Anomalies are not something that you look for outside your data. 2. They are already in your data. 3. You just need to know how to look.
- 16. A Very Simple Example
- 17. The error in the First Slide. 1. A spelling error. 2. Due to years of reading and training our minds we identify spelling errors immediately. – A default context, frame of reference. With Error Corrected
- 18. A Second Pass 1. The letter “y” is italicized. 2. With years of training we can almost immediately differentiate roman and italics. Another default context, frame of reference. Italicized Roman
- 19. A Third Pass 1. The letter “t” is in a smaller size font. 2. Not obvious, change of context. 3. Because we focus on the information from the text, not of the text. Font 32 Font 36