Scraping Moody's: Digitizing Financial and Accounting Information from Images

The Department of Information Science Presents:
Dr. Diego Garcia|
Burridge Endowed Chair
Leeds School of Business
University of Colorado Boulder

ABSTRACT:
The talk will discuss how a team at the Leeds School is digitizing a set 
of historical manuals (the Moody's Manuals of Investment, 1909-1952). 
The challenges of image collection/curing, as well as those associated 
with different types of optical character recognition (OCR) algorithms, 
will be the focus of the discussion. Besides the technicalities behind 
OCR techniques and image manipulations, we will touch on the breadth of 
data in the Moody's manuals, highlighting potential interdisciplinary ideas.

BIOGRAPHY:
Diego Garcia is the Burridge Endowed Chair in Finance at the Leeds 
School of Business. Professor Garcia was on the faculty at UNC at Chapel 
Hill and at the Tuck School of Business before joining the University of 
Colorado at Boulder. He received his PhD from the Haas School of 
Business and his master's in Statistics from the College of Letters and 
Science at the University of California, Berkeley. Professor Garcia 
comes from Asturias, a small region in Northwest Spain. His research 
interest encompass informational frictions in financial markets, as well 
as the effect of behavioral biases in asset prices. His work is both 
theoretical and empirical in nature.

Webpage with more details http://leeds-faculty.colorado.edu/garcia/

ABOUT:
The Information Science seminar is a weekly talk series and gathering for the Information Science department and its extended community. Any faculty, students, and interested parties regardless of affiliation are welcome. Keep an eye out for future announcements!

Click here to see a calendar of upcoming INFO seminars

Click here to watch videos from past seminars

Wednesday, April 3 at 1:00pm to 2:00pm


University Memorial Center (UMC), 247
1669 Euclid Avenue, Boulder, CO 80309

Recent Activity