Claims Fraud Detection for P&C Insurance

August 15, 2020

Leading Personal Lines Insurance Carrier in NE of US

Problem Statement

• Basic business rules for fraud detection and prevention was in place and the need for improving their fraud detection and prevention tools was considered
• A POC was developed to analyze Customers’ claims data to provide trends and patterns of suspected fraudulent transactions

Analytics Led Approach

• Given are high level process steps which were followed:
  • Sensitive data encryption
  • Load the data from
  • multiple sources Logistic Regression Model creation
  • Data cleansing ; Data transformation; Business Significant variables deduction
  • Distribution analysis
  • Correlation analysis
  • Multi- dimensional Analysis
  • Fraud analysis through data profiling
  • Identify key suspect indicators which indicated possible provider frauds

Business Impact

• Designed a proof of concept whereby Customers’ auto claims data for specific calendar year were analyzed and trends and patterns from analysis  were presented
• The solution helped to identify the potential losses due to fraud or suspect claims and thereby helped to reduce claims leakage to a great extent

Critical Success Factors

• $ 3.5 million potential losses were identified due to potential suspects
• $ 600 k of potential losses were identified due to potential suspects with fortune coverage