Claims Subrogation Analytics

3AI August 15, 2020

Leading US Health Insurance Company

Problem Statement

• Annual revenue leakage because of subrogation non-recovery: ~ $79.2 MN
• Subrogation recovery rate: 4 %
• Business objective was to analyze closed subrogation cases and identify case segments having high propensity of recovery, so that focused attempt can be made to recover them

Analytics Led Approach

• Given are high level process steps which were followed

  • Distribution analysis ; Correlation analysis ;Anova
  • Original Amount, LOS, Age, Units Billed, DX (transformed) ; # of Claim Lines
  • Test, Control split ; Logistic Regression model development; Model selection
  • False positives, true negatives comparison for cut off determination
  • Insights and business rules formulation

Business Impact

• Predictive analytical model was designed to identify case segments having high propensity for subrogation recovery
• A systematic approach to transform the model results into business rules, that can augment current subrogation process making it more effective was framed as well

Critical Success Factors

• A potential recovery rate increase of 8% – 22 % for cases with >60% of subro potential
• Opportunity to plug in revenue leakage of USD ~5 MN has been addressed
• Additional business rules to prioritize cases for subrogation recovery that can seamlessly integrate within existing workflow