Richard A. Derrig Ph. D. OPAL Consulting LLC Visiting Scholar, Wharton School University of Pennsylvania Daniel Finnegan Quality Planning Corp Innovative Solutions ISO Fraud Fighting Actuaries Mathematical Models for Insurance Fraud Detection CAS Predictive Modeling September 19-20, 2005
ACTUARIAL PROBLEMS W WHAT: Product Design W WHERE: Market Characteristics W WHO: Classification & Sale W HOW: Claims Paid W WHEN: Forecasting W WHY: Profit (Expected)
TRADITIONAL MATHEMATICAL TECHNIQUES W Arithmetic (Spreadsheets) W Probability & Statistics (Range of Outcomes) W Curve Fitting (Interpolation & Extrapolation) W Model Building (Equations for Processes) W Valuation (Risk, Investments, Catastrophes) W Numerical Method (Analytic Solution Rare)
NON-TRADITIONAL MATHEMATICS W Fuzzy Sets & Fuzzy Logic uElements: “in/out/partially both” uLogic: “true/false/maybe” uDecisions: “incompatible criteria” W Artificial Intelligence: “data mining” W Neural Networks: “learning algorithms” W Classification and Regression Trees
CLASSIFICATION W Segmentation: A major exercise for insurance underwriting and claims W Underwriting: Find profitable risks from among the available market W Claims: Sort claims into easy pay and claims needing investigation
FRAUD W The Major Questions uWhat Is Fraud? uHow Much Fraud is There? uWhat Companies Do about Fraud? uHow Can We Identify a Fraudulent Claim?
FRAUD DEFINITION Principles Clear and willful act Proscribed by law Obtaining money or value Under false pretenses Abuse/ Ethical Lapse: Fails one or more Principles
FRAUD TYPES W Insurer Fraud uFraudulent Company uFraudulent Management W Agent Fraud uNo Policy uFalse Premium W Company Fraud uEmbezzlement uInside/Outside Arrangements W Rating and Claim Fraud uPolicyholder/Claimant/Insured uProviders/Rings
OTHER FRAUD W MGAs W TPAs W Primary Insurers W Commercial Lines (auto, wc) W Claim Fraud W Premium Fraud (wc) W Auditing W Data Availability W Data Manipulation W Fraud Plans
TYPES OF CLAIM FRAUD AUTO W Bodily Injury -Staged Accidents -Actual Accidents/Faked Injuries -Jump-Ins -Provider Abuse / False Billing W Vehicle Damage -Staged Thefts -Chop Shops -Body Shop Fraud -Adjuster Fraud
TYPES OF CLAIM FRAUD WORKERS’ COMPENSATION W Employee Fraud -Working While Collecting -Staged Accidents -Prior or Non-Work Injuries W Employer Fraud -Misclassification of Employees -Understating Payroll -Employee Leasing -Re-Incorporation to Avoid Mod
HOW MUCH CLAIM FRAUD?
10% Fraud
HOW MUCH FRAUD?
ALL FRAUD W What Can Be Done?
WHAT COMPANIES DO ABOUT FRAUD W Investigate Investigation reduces BI Claim payments by 18 percent. Additional investigation not cost-effective. Better claim selection may be cost-effective. W Negotiate Negotiation reduces BI claim payments on build-up claims by 22 percent compared to valid claims with same medicals, injuries, etc. W Litigate Litigation of bogus claims results in high number of company verdicts. When effective, claim withdrawals and closed-no-pay increase.
THEORY OF CLAIM FRAUD W Utility Maximization UTL (Fraud v. No Fraud) W Asymmetric Information Inf (Claimant/Provider v. Insurer) W Welfare Loss WFL (Detection $ v. Fraud $) _________________________________ W All Rely on Detection Probabilities
THE INSURER’S PROBLEM W Self-interested behavior of claimants W Asymmetric information W Attitudes and social norms
FRAUD AND ABUSE THE TOP TEN DEFENSES W 1. Adjusters W 2. Computer Technology W 3. Criminal Investigators W 4. Data and Information W 5. Experts W 6. Judges W 7. Lawyers W 8. Legislators W 9. Prosecutors W 10. Special Investigators
REAL CLAIM FRAUD DETECTION PROBLEM W Classify all claims W Identify valid classes uPay the claim uNo hassle uVisa Example W Identify (possible) fraud uInvestigation needed W Identify “gray” classes uMinimize with “learning” algorithms
DM Databases Scoring Functions Graded Output Non-Suspicious Claims Routine Claims Suspicious Claims Complicated Claims
Settlement Ratios by Injury and Suspicion VariablePIP Suspicion Score = Low (0-3) PIP Suspicion Score = Mod to High (4-10) PIP Suspicion Score = All 1996 (N-336) 1996 (N-216) 1996 (N-552) Str/SPAll OtherStr/SPAll OtherStr/SPAll Other Settlement 81%19%94%6%86%14% Avg. Settlement/ Specials Ratio Median Settlement/ Specials Ratio
DATA
POTENTIAL VALUE OF AN ARTIFICIAL INTELLIGENCE SCORING SYSTEM W Screening to Detect Fraud Early W Auditing of Closed Claims to Measure Fraud W Sorting to Select Efficiently among Special Investigative Unit Referrals W Providing Evidence to Support a Denial W Protecting against Bad-Faith
Examples of Fraud Detection l Dan Finnegan