2009 INFORMS Data Mining Contest
The results have been posted on the results page and some participants have provided short abstracts!
Here are the slides about the contest that were presented at INFORMS
The 2009 INFORMS Data Mining Contest is the second installation of a data mining contest that started last year in conjunction with the INFORMS conference. This year's contest is co-organized on behalf of INFORMS by the Predictive Modeling Group at IBM Research and Health Care Intelligence (HCI-LLC). Once again we will focuses on predictive problems for health care quality. The two tasks for this year's contest are: 1) modeling of a patient transfer guideline for patients with a severe medical condition from a community hospital setting to tertiary hospital provider and 2) assessment of the severity/risk of death of a patient's condition. For further information and motivation on the healthcare objectives see the background. For description of the modeling tasks see Task Description and Instructions sections of this website.
The contest is over at this time! Thanks to all the participants for their hard work and see you at INFORMS!
If you are interested in the data and working on health-care quality, please contact the organizer Paul Savage.
Data Mining and Machine Learning at IBM Research
The Predictive Modeling Group at the IBM T.J. Watson Research Center in Yorktown Heights, New York conducts research in many areas of data mining, machine learning, and statistical modeling, with a particular focus of applying these techniques to challenging real-world data-analytics problems. Our work in analytics-based approaches to improving sales productivity was selected as a Finalist for the 2009 INFORMS Franz Edelman Award. We have submitted winning solutions to the 2007, 2008, and 2009 KDD Cup Competitions, as well as the 2008 INFORMS Data Mining Competition.
Business Intelligence offerings at HealthCare Intelligence
HealthCare Intelligence from Stamford, Connecticut is a service provider for hospital management. Our patient modeling, forecasting and Dashboard visualization tools are seen as a new generation of competitive intelligence, and is now available to healthcare leaders. Our work in Health Care Management and Quality Improvement has included sponsoring presentations and tracks at the International Symposium on Forecasting for the International Institute of Forecasters in 2005 and 2007. We are proud to support this contest with a real-world domain in assembling concise data resources and focusing on the types of decision problems faced by front line executives in the Health Care field.