BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Do U.S. Financial Regulators Listen to the Public? Testing the Reg
 ulatory Process with the RegRank algorithm - Kirilenko\, A (Massachusetts 
 Institute of Technology)
DTSTART:20141218T163000Z
DTEND:20141218T171500Z
UID:TALK56693@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Co-authors: Shawn Mankad (University of Maryland)\, George Mic
 hailidis (University of Michigan) \n\nWe examine the notice-and-comment pr
 ocess and its impact on influencing regulatory decisions by analyzing the 
 text of public rule-making documents of the Commodity Futures Trading Comm
 ission (CFTC) and associated comments. For this task\, we develop a data m
 ining framework and an algorithm called RegRank\, which learns the themati
 c structure of regulatory rules and public comments and then assigns tone 
 weights to each theme to come up with an aggregate score for each document
 . Based on these scores we test the hypothesis that the CFTC adjusts the f
 inal rule issued in the direction of tone expressed in public comments. Ou
 r findings strongly support this hypothesis and further suggest that this 
 mostly occurs in response to comments from the regulated financial industr
 y. We posit that the RegRank algorithm and related text mining methods hav
 e the potential to empower the public to test whether it has been given th
 e "due process" and hence keep government agencies in chec k.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR