India's largest platform and marketplace for AI & Analytics leaders & professionals

Sign in

India's largest platform and marketplace for AI & Analytics leaders & professionals
Become a Thought Leader
Become a 3AI Member

Sign in

3AI Digital Library

< Go Back

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

    3AI Trending Articles

  • Chess and AI

    “It’s just a machine. It has no consciousness or feelings as we understand them. We have specific connections in our brain that make us react according to the circumstances, the situations we are experiencing. We interpret them as pleasure, pain and all other kinds of emotions. We would have to invent a new word to […]

  • How Augmented Analytics is Transforming the Analytics Ecosystem

    Author:  Sidharth Sivasailam, Vice President – Products, Course5 Intelligence | LinkedIn – https://www.linkedin.com/in/sidharthsiva/ The world of Business Analytics is at an inflection point. Trillions of bytes of data are being generated every day; however, companies continue to struggle with harmonizing this data, analyzing the data of various shapes and sizes they are storing, determining what’s […]

  • Data Science redefines Consulting to transform Digital Business Model

    Consulting firms the world over, are looking to develop competencies that would create a definite competitive advantage for them in the market. The consulting sector is no longer immune to disruptive technologies that have significantly influenced other digital-enabled businesses and is flooded with new players having a non-traditional approach toward consulting. Globally, companies seeking a […]

  • Way to make object-recognition models perform better

    Adding a module that mimics part of the brain can prevent common errors made by computer vision models. Computer vision models known as convolutional neural networks can be trained to recognize objects nearly as accurately as humans do. However, these models have one significant flaw: Very small changes to an image, which would be nearly […]