Fraud Detection and Deterrence in Workers’ Compensation

1
Fraud Detection and Deterrence in Workers
Compensation

• Richard A. Derrig, PhD, CFE
• President Opal Consulting, LLC
• Visiting Scholar, Wharton School,
• University of Pennsylvania

PCIA Joint Marketing and Underwriting
Seminar March 18-20, 2007
2
Insurance Fraud- The Problem

• ISO/IRC 2001 Study Auto and Workers Compensation
  Fraud a Big Problem by 27 of Insurers.
• CAIF Estimation (too large)
• Mass IFB 1,500 referrals annually for Auto, WC,
  and (10) Other P-L.

3
Fraud Definition

• PRINCIPLES
• Clear and willful act
• Proscribed by law
• Obtaining money or value
• Under false pretenses
• Abuse Fails one or more Principles

4
HOW MUCH CLAIM FRAUD? (CRIMINAL or
CIVIL?)
5
10 Fraud
6
REAL PROBLEM-CLAIM FRAUD

• Classify all claims
• Identify valid classes
• Pay the claim
• No hassle
• Visa Example
• Identify (possible) fraud
• Investigation needed
• Identify gray classes
• Minimize with learning algorithms

7
Company Automation - Data Mining

• Data Mining/Predictive Modeling Automates Record
  Reviews
• No Data Mining without Good Clean Data (90 of
  the solution)
• Insurance Policy and Claim Data Business and
  Demographic Data
• Data Warehouse/Data Mart
• Data Manipulation Simple First Complex
  Algorithms When Needed

8
DATA
9
Computers advance

•  
•  
•  

10
FRAUD IDENTIFICATION

• Experience and Judgment
• Artificial Intelligence Systems
• Regression Tree Models
• Fuzzy Clusters
• Neural Networks
• Expert Systems
• Genetic Algorithms
• All of the Above

11
(No Transcript)
12
(No Transcript)
13
POTENTIAL VALUE OF AN ARTIFICIAL INTELLIGENCE
SCORING SYSTEM

• Screening to Detect Fraud Early
• Auditing of Closed Claims to Measure Fraud
• Sorting to Select Efficiently among Special
  Investigative Unit Referrals
• Providing Evidence to Support a Denial
• Protecting against Bad-Faith

14
Implementation Outline Included at End

15
CRIMINAL FRAUD? (Massachusetts)
16
(No Transcript)
17
Prosecution Study Mass. IFB Data
1990-2000

• 17,274 Referrals 59 auto, 31 wc, 35 accepted
  for investigation.
• 3,349 Cases, i.e. one or more related accepted
  referrals.
• 552 Cases were referred for prosecution293 cases
  had prosecution completed.

18
Prosecution Study Mass. IFB Data
1990-2000

• Case Outcomes No Prosecution (CNP)
• Prosecution Denied (PD),
  Prosecution Completed (PC)
• Auto Cases 1,156 CNP,50 PD,121PC
• WC Claim 524 CNP,40 PD, 82PC
• WC Premium 70 CNP, 9 PD, 34PC

19
Subjects Prosecuted

• 543 subjects were prosecuted
• 399 were claimants/insureds
• 65 were insureds only
• 46 were professionals associated with the
  insurance system as company personnel or service
  providers

20
Prosecution Findings

• Guilty or Equivalent 84
• Pled Guilty 55
• Continued without a Finding 19
• Not Guilty 8
• Not Disposed (Fled) 3
• Other (e.g. filed) 5

21
Sentences

• Jail 205/471(44)
• Jail to Serve 88/205 (43)
• Probation 292/471 (62)
• Restitution 272/471 (58)
• Fines 175 (37)
• Professionals have most Jail (59) and most Jail
  to Serve (44)
• Source Table 5

22
Sentencing Outcomes II

• See Figure 5, p92 of Paper
• Jail Time (to Serve) in months
• Insured/Claimant 18.7 (12.9)
• Insured Only 25.0 (22.6)
• Professionals 24.7 (8.8)
• All 19.5 (13.1)
• IFB Sentences consistent with 1996 countrywide
  fraud convictions.

23
Fraudsters

• Prior Convictions 51
• Prior Property Conviction 9.6
• Subsequent Offenses 29
• Subsequent Offense Prior to End of Fraud Sentence
  19
• Conclusion These are general purpose criminals
  not career insurance fraudsters!

24
Criminal Fraud Deterrence

• General Deterrence Mixed results
• Specific Deterrence Good Results
• Big Deterrence There is nothing comparable to
  the Lawrence Deterrent

25
Insurance Fraud Bureau of
Massachusetts

• 2003 Lawrence Staged Accident Results In Death
• IFB Joined w/Lawrence P.D and Essex County DAs
  Office to form 1st Task Force

26
Insurance Fraud Bureau of Massachusetts

• Results 2005-2006

• Total Cases referred to Pros. 244
• Total Individuals Charged 528

27
TYPES OF FRAUD

• WORKERS COMPENSATION
• Employee Fraud
• -Working While Collecting
• -Staged Accidents
• -Prior or Non-Work Injuries
• Employer Fraud
• -Misclassification of Employees
• -Understating Payroll
• -Employee Leasing
• -Re-Incorporation to Avoid Mod

28
NON-CRIMINAL FRAUD?
29

NON-Criminal Fraud Deterrence Workers
Compensation

• General Deterrence DIA, Med, Att Government
  Oversight
• Specific Deterrence Company Auditor, Data,
  Predictive Modeling,
• Employer Incentives (Mod, Schd Rate)
• Big Deterrence None, Little Study, NY Fiscal
  Policy Institute (2007)
• CA SIU Regulations (2006)

30
FRAUD INDICATORSVALIDATION PROCEDURES

• Canadian Coalition Against Insurance Fraud (1997)
  305 Fraud Indicators (45 vehicle theft)
• No one indicator by itself is necessarily
  suspicious.
• Problem How to validate the systematic use of
  Fraud Indicators?

31
Underwriting Red Flags

• Prior Claims History (Mod)
• High Mod versus Low Premium
• Increases/Decreases in Payroll
• Changes of Operation
• Loss Prevention Visits
• Preliminary Physical Audits
• Check Yellow Pages
• Check Websites

32
Claims Red Flags

• Description of Accident vs. Underwriting
  Description of Operation
• Description of Employment
• Length of Services/Supervisor
• Pay
• Kind of Work
• Copies of Payroll Checks
• Claims vs. Payroll

33
Auditing Red Flags

• Be Aware of Prepared Documents
• Check Original Files
• Check Loss Reports
• Check Class Distribution
• Estimated Payroll Compared to Audited Payroll
• Prior Claims
• Changes of Operations

34
POLICY
Estimated Premium Audited /Adjusted Premium
35
WORKERS COMPENSATION PREMIUM TERMINOLOGY

• Payroll - All Compensation
• Classification Rate - Based on Type of Job (Risk
  of Injury)
• Mod - Multiplier Based on Claims History

36
WORKERS COMPENSATION PREMIUM FORMULA

• Payroll x Classification Code x Experience Mod

37
TYPES OF PREMIUM FRAUD

• Payroll Misrepresentation
• Classification Misrepresentation
• Modification Avoidance

38
(No Transcript)
39
Case Study Lanco Scaffolding

• Lanco Representations
• Small scaffolding operation
• Limited accounting records
• Outside accountant prepared and possessed tax
  records
• Premium of 28,000

40
Lanco Scaffolding, Inc.
41
(No Transcript)
42
(No Transcript)
43
AUDIT PROCESS

• Auditor spends 2-3 hours on site, reviewing
  records provided by the insured (payroll, tax
  records, jobs)
• Auditor compares these with insurance records
  (claims history, prior audits, loss prevention
  reports)

44
INSURANCE RECORDS

• Audit Reports
• -Work Papers
• -Supporting Documents from Insured
• Claim/Loss Runs
• Underwriting Documents
• -Agent
• -Insured
• Loss Prevention Reports

45
BAD AUDIT
46
GOOD AUDIT
47
SIU INVOLVEMENT

• What is the Issue?
• Referrals can be Optimized
• Review Company Files
• Surveillance
• Interview Agent
• Interview Insured
• Interact with Fraud Bureau

48
REFERENCES

• Canadian Coalition Against Insurance Fraud,
  (1997) Red Flags for Detecting Insurance Fraud,
  1-33.
• Derrig, Richard A. and Krauss, Laura K., (1994),
  First Steps to Fight Workers' Compensation Fraud,
  Journal of Insurance Regulation, 12390-415.
• Derrig, Richard A., Johnston, Daniel J. and
  Sprinkel, Elizabeth A., (2006), Risk Management
  Insurance Review, 92, 109130.
• Derrig, Richard A., (2002), Insurance Fraud,
  Journal of Risk and Insurance, 693, 271-289.
• Derrig, Richard A., and Zicko, Valerie, (2002),
  Prosecuting Insurance Fraud A Case Study of the
  Massachusetts Experience in the 1990s, Risk
  Management and Insurance Review, 52, 7-104
• Francis, Louise and Derrig, Richard A., (2006)
  Distinguishing the Forest from the TREES A
  Comparison of Tree Based Data Mining Methods,
  Casualty Actuarial Forum, Winter, pp.1-49.
• Johnston, Daniel J., (1997) Combating Fraud
  Handcuffing Fraud Impacts Benefits, Assurances,
  652, 175-185.
• Rempala, G.A., and Derrig, Richard A., (2003),
  Modeling Hidden Exposures in Claim Severity via
  the EM Algorithm, North American Actuarial
  Journal, 9(2), pp.108-128.