DataMiningApproachestoModelingInsuranceRisk.pptVIP

Data Mining Opportunities in Health Insurance;Analytical Challenges for Health Insurance;Analytical Opportunities;Why Data Mining Has Changed the Game;Importance of Interactions;Further Data Mining Capabilities;Examples of Data Mining in Actionfor Health Insurance;Cases StudiesBy Users of CART?, MARS?, TreeNet?;Case Study: Worker’s Compensation Predicting Serious Claims at Case Outset ;Examples of Data available: About claim: Dates of registration and closing Was the claim reopened? Was the claim litigated? Liability estimates Payments made Was claim reporting delayed? About claimant: Gender, age, family/dependents Employment type, occupation, work duties Wages About injury or disease: Time and place Location on body Cause or mechanism;“Serious Claim” defined as: Claimant received payment at least three months (time off work) AND/OR Claim was litigated Modeling based on a random sample of cases injury occurred 18-24 months prior to the latest claim;Results: 19 predictive predictors selected from 83 candidates Some predictors expected ( nature and location of injury) Some unexpected (like claimant language skills) Classified 32% of all claims as serious (test data) ;Misclassification tables;Model Assessment: Gains chart:;Case Study: Modeling Total Projected Customer Value for a Health Insurer;Data used for hospital claim frequency and cost sub-model: Covered a 36-month period Predicted outcomes for next 12 months using data from previous 24 months About 300 variables as potential predictors: Demographic (age, gender, family status) Geographic and socio-economic (residence location, indices on education, advantage/disadvantage) Membership and product (membership duration, product held) Claim history and medical diagnosis Miscellaneous data (distribution channel, payment method, etc.);Hospital claim frequency and cost sub-model divided into two sub-models: Predict probability of at least one claim over past 12 months Predict cost given at least one claim D