This looks like quite an interesting talk:

Machine Learning and Electronic Financial Markets

Andrei Kirilenko
Chief Economist, Commodities and Futures Trading Commission (CFTC)
18 March 1:30PM – Dome Room, Rotunda

During the last several years, financial markets have rapidly transitioned from face-to-face to anonymous electronic trading. This transition called for a significant overhaul of regulatory surveillance practices, which were largely based on the principles of human rather than algorithmic trading. How do the machines trade in electronic markets? How are the prices discovered? How robust are the markets populated by the machines? I will discuss quantitative applications of three machine-learning methods to regulatory, audit-trail data. The methods are Plaid clustering, Hidden Markov chain, and network analysis. I will conclude with the analysis of the events of May 6, 2010 – the Flash Crash – the first financial market crash of the machine-trading era.

Speaker Biography
Andrei Kirilenko, Chief Economist, has been with the Commodity Futures Trading Commission (CFTC) since 2008 and was appointed Chief Economist in December 2010. He received his Ph.D. in Economics from the University of Pennsylvania, where he specialized in financial markets. Prior to joining the CFTC, Dr. Kirilenko spent twelve years at the International Monetary Fund working on global capital markets issues. His research has focused on the informational properties and microstructure of securities and derivatives markets. He has published a number of journal articles appearing in the Journal of Finance, Journal of Financial Markets, and IMF Staff Papers. In 2010, Dr. Kirilenko was the recipient of the CFTC Chairman’s Award for Excellence (highest honor).