Title page for E-project-042607-172532

Project Type MQP

Submission date 2007-04-26

Authors
Joanna B Kluza, MAC
Joseph F Kraynak, MAC
William Treese, MAC
Jaris B Wicklund, MAC

URN E-project-042607-172532

Sponsor John Hancock

Title Long Term Care Underwriting Risk Scoring Model

Advisors
Heinricher, Arthur C, MA
Abraham, Jon P, MA

Availability unrestricted

Abstract
The project goal was to test a previously designed adaptive risk scoring model for long term care insurance underwriting using actual applicant data from John Hancock. A data filtering method for removing applicants who should not be used to train the model was developed. The model provides accurate risk class assignment, based solely on the medical conditions, when trained on the filtered data. In addition, the model identifies errors in the risk points assigned to individual medical conditions.

Files
LongTermCareMQP.pdf

Browse by Author | Browse by Department | Search all available E-projects

Questions? Email project-questions@wpi.edu
Maintained by webmaster@wpi.edu

Project Type	MQP
Submission date	2007-04-26
Authors	Joanna B Kluza, MAC Joseph F Kraynak, MAC William Treese, MAC Jaris B Wicklund, MAC
URN	E-project-042607-172532
Sponsor	John Hancock
Title	Long Term Care Underwriting Risk Scoring Model
Advisors	Heinricher, Arthur C, MA Abraham, Jon P, MA
Availability	unrestricted
Abstract The project goal was to test a previously designed adaptive risk scoring model for long term care insurance underwriting using actual applicant data from John Hancock. A data filtering method for removing applicants who should not be used to train the model was developed. The model provides accurate risk class assignment, based solely on the medical conditions, when trained on the filtered data. In addition, the model identifies errors in the risk points assigned to individual medical conditions.
Files	LongTermCareMQP.pdf