Method and system for identifying consumer credit revolvers with neural network time series segmentation

US6556979B1 · kind B1 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Shiping Liu · Columbia, US
• Edgar Leroy Murphy, Jr. · Southlake, US
• David W. Nanek · Stormville, US
• Michael A. Rothman · Puyallup, US

Key dates

• Filing date: Jun 19, 2000
• Grant date: Apr 29, 2003
• Expiry date: May 16, 2021

Classification

• Technology area (CPC G): Physics
• CPC primary: G06Q40/03
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Initially, customer time series credit files are acquired. The credit files are organized in a data mart environment for supporting a query system. Time series utilization attributes are created and a neural network time series segmentation process is applied and N×N dimension segments are generated for analysis. The chart may be modified to more accurately depict profitable credit revolvers. Credit data from each potential new customer is processed in a similar fashion by the neural network segmentation process. Profitable credit revolvers are identified by having credit utilization patterns belonging to profitable segments previously identified.