SCIENCE
Modelers Prove Their Mastery in Allstate's Claim Prediction Challenge
- Written by: Webmaster
- Category: SCIENCE
Competitors Size Up Data Analysis Skills in Crowd Sourcing Contest
After a three-month long crowd sourcing competition, three data scientists proved their data analysis abilities in Allstate's predictive modeling competition. The nation's largest publicly-held insurer launched the "Claim Prediction Challenge" with Kaggle on July 13, offering $10,000 to number crunchers worldwide for the best models predicting bodily injury insurance claims based on vehicle characteristics.
Contestants continued to submit algorithms down to the competition's closing minutes October 12. From 1290 total submissions and 202 players, the three winners with models closest to predicting actual claims data are:
-- 1st place - $6,000 - Matthew Carle - Sydney, Australia
-- 2nd place - $3,000 - Owen Zhang - Bolton, Conn., USA
-- 3rd place - $1,000 - Jason Tigg - London, United Kingdom
Aside from monetary motivation, all three winners said they entered to size up their skills against some of the best predictive modeling talents out there. The public leader board on the competition site fueled continual model improvements and additional entries.
"As an actuary, I have worked on claims models in the past, and the Claim Prediction Challenge allowed me to see how my modeling skills compare with those of other modeling experts," said Carle. "It also provided a way to improve modeling skills and try new techniques."
Provided with Allstate data from 2005 to 2007, contestants analyzed correlations between vehicle characteristics and bodily injury claims payments to predict claims payment amounts in 2009. Based on the data, modelers considered how factors such as horsepower, length and number of cylinders affect an insured's likelihood of being held responsible for injuring someone in a car accident. The data provided to contestants contained no personal information about any individual consumers.
"A competition of this type is definitely a new approach for the property and casualty insurance industry, and we're proud to reward the work of these talented winners," said Allstate Vice President Eric Huls, Quantitative Research and Analytics. "Allstate always looks for ways to embrace new ideas and appreciates the excitement and participation generated in this community of modelers."
Allstate will examine the winning modelers' methods and may use gained insights to complement the insurer's existing best-in-class modeling techniques.
"We're excited to see Allstate helping to advance actuarial science by engaging the best and brightest data scientists from around the world," said Anthony Goldbloom, founder and chief executive officer, Kaggle. "Kaggle's competitive dynamic inherently pushes entrants to produce better work than they would have if they were working in isolation, so they break the benchmark time and time again. This ultimately leads to greater efficiency for companies like Allstate."
After a three-month long crowd sourcing competition, three data scientists proved their data analysis abilities in Allstate's predictive modeling competition. The nation's largest publicly-held insurer launched the "Claim Prediction Challenge" with Kaggle on July 13, offering $10,000 to number crunchers worldwide for the best models predicting bodily injury insurance claims based on vehicle characteristics.
Contestants continued to submit algorithms down to the competition's closing minutes October 12. From 1290 total submissions and 202 players, the three winners with models closest to predicting actual claims data are:
-- 1st place - $6,000 - Matthew Carle - Sydney, Australia
-- 2nd place - $3,000 - Owen Zhang - Bolton, Conn., USA
-- 3rd place - $1,000 - Jason Tigg - London, United Kingdom
Aside from monetary motivation, all three winners said they entered to size up their skills against some of the best predictive modeling talents out there. The public leader board on the competition site fueled continual model improvements and additional entries.
"As an actuary, I have worked on claims models in the past, and the Claim Prediction Challenge allowed me to see how my modeling skills compare with those of other modeling experts," said Carle. "It also provided a way to improve modeling skills and try new techniques."
Provided with Allstate data from 2005 to 2007, contestants analyzed correlations between vehicle characteristics and bodily injury claims payments to predict claims payment amounts in 2009. Based on the data, modelers considered how factors such as horsepower, length and number of cylinders affect an insured's likelihood of being held responsible for injuring someone in a car accident. The data provided to contestants contained no personal information about any individual consumers.
"A competition of this type is definitely a new approach for the property and casualty insurance industry, and we're proud to reward the work of these talented winners," said Allstate Vice President Eric Huls, Quantitative Research and Analytics. "Allstate always looks for ways to embrace new ideas and appreciates the excitement and participation generated in this community of modelers."
Allstate will examine the winning modelers' methods and may use gained insights to complement the insurer's existing best-in-class modeling techniques.
"We're excited to see Allstate helping to advance actuarial science by engaging the best and brightest data scientists from around the world," said Anthony Goldbloom, founder and chief executive officer, Kaggle. "Kaggle's competitive dynamic inherently pushes entrants to produce better work than they would have if they were working in isolation, so they break the benchmark time and time again. This ultimately leads to greater efficiency for companies like Allstate."