JSM 2005 - Toronto

Abstract #304285

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2005); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.



The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page
Legend: = Applied Session, = Theme Session, = Presenter
Activity Number: 139
Type: Contributed
Date/Time: Monday, August 8, 2005 : 10:30 AM to 12:20 PM
Sponsor: Business and Economics Statistics Section
Abstract - #304285
Title: Building Uncorrelated Models for Consumer Lending: A practitioner's Review of Applications
Author(s): Alex Strounine*+
Companies:
Address: 119 Winthrop Rd Apt 3, Brookline, MA, 02445, United States
Keywords: Consumer Credit ; Credit Risk ; Predictive Modeling ; Uncorrelated Models ; Adverse Selection ; Risk Adjusted Response Models
Abstract:

Predictive analytics problems in the consumer credit industry commonly have multivariable objectives. Frequently, the variables are strongly correlated and have opposite effects on business profitability. For example, increased consumer demand for credit, which has positive effect on the industry, is strongly correlated with increased risk of default on financial obligations, which in turn has negative effect on the industry. In cases such as that, classic predictive models usually produce suboptimal results---a credit card response model is correlated with credit risk and therefore does not identify most profitable customers. In this paper, we show methods developed to solve constrained optimization problems can be successfully used to build a statistical model that predicts one outcome and is uncorrelated with a set of other outcomes. We present an exposition of several applications of uncorrelated models to lending industry and compare them to traditional regression models. Case studies include credit card response and usage models not correlated with credit risk, a fraud model, and a new concept of loan pricing strategy as an alternative to traditional risk-based pricing.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2005 program

JSM 2005 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2005