System for funding future workers compensation losses

• US 5,613,072 A
• Filed: 06/01/1995
• Issued: 03/18/1997
• Est. Priority Date: 02/06/1991
• Status: Expired due to Term

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Risk Data Corp. (Fair Isaac Corporation)
• Inventors: Hammond, Mark S., Bianco, Vincent J., Bonk, James W., Zwanziger, Jack
• Primary Examiner(s): Hayes, Gail O.
• Assistant Examiner(s): Yount, Steven R.
• Application Number:
  US08/456,492
• Time in Patent Office: 656 Days
• Field of Search: 364/401, 364/406, 364/408
• US Class Current: 705/4
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A system is disclosed for funding future losses incurred by an insurance carrier on active workers'"'"' compensation insurance claims. The system uses statistical models to predict future costs and durations of an insurance carrier'"'"'s claims. The statistical models are generated by applying statistical analysis techniques to representative historical insurance claim data with the aid of a professional statistician. Forecasting accuracy is improved by generating several models wherein each model represents a predefined type of insurance claim. Each model is applied to the carrier'"'"'s active claims of the corresponding type to obtain cost and duration predictions for those claims. A total cost prediction for a claim is proportioned among various cost categories to more accurately reflect actual and predicted claim costs. For each claim, a reserve amount is calculated which is the predicted cost minus the amount of money paid to date on the claim. Balancing of the respective reserve amounts computed for active claims is achieved by use of a hypothetical fund which transfers reserve money from overpredicted claims to the reserves of underpredicted claims. A total reserve amount is calculated for each claim, and an aggregate reserve amount is calculated for all the carrier'"'"'s active claims. The aggregate reserve amount is used to set a loss reserve account maintained by the carrier to fund future losses incurred on those claims. The system includes a system computer and program used for generation of the statistical models, a carrier-accessible computer for housing the models for application to active claims, and a carrier host computer for storing and updating the active claims of the insurance carrier.

Claims

1. A method for accurately predicting future losses to be incurred by an insurance carrier on insurance claims on a claim by claim basis, said method comprising the steps of:

collating historical data on insurance claims having known cost values and which are representative of expected future insurance claims to be funded and storing said historical data in a first memory storage area;

retrieving said historical data from said first memory storage area and generating one or more statistical models representative of said cost values of said historical insurance claims based upon significant characteristics of said historical insurance claims;

storing and maintaining said statistical models in a second memory storage area accessible by an insurance carrier;

storing information regarding active insurance claims including selected significant characteristics for each particular active insurance claim of said insurance carrier in a third memory storage area;

reading said information stored in said third memory storage area;

applying said models stored in said second memory storage area to said significant characteristics of each particular active insurance claim of said insurance carrier models to obtain an individual future cost prediction for each particular active claim;

calculating an individual reserve amount for each particular active claim based on the individual cost prediction for each particular active claim; and

placing money in a loss reserve account based on said calculated individual reserve amount for each particular active claim to fund future losses incurred on said particular active claim.

2. The method of claim 1, further comprising the step of updating said information stored in said third memory storage area in response to real events occurring with respect to said active insurance claims.

3. The method of claim 1, further comprising the step of setting premiums for a client of said insurer based upon the total individual cost predictions for all active claims of said client.

4. A method for predicting future costs to be incurred by an insurance carrier on workers'"'"' compensation injury claims on a claim by claim basis, said method comprising the steps of:

collating historical workers'"'"' compensation claim data from one or more insurance carriers for claims processed within a defined territory such as a state and storing said claim data in a first data storage area;

retrieving said historical workers'"'"' compensation claim data from said first data storage area and generating a plurality of statistical models, wherein each model is determined by and is representative of significant characteristics of a data subset of claims, and wherein each data subset comprises claims of a predefined type;

storing said statistical models in a second data storage area accessible by the insurance carrier;

reading data files containing data on the insurance carrier'"'"'s active workers'"'"' compensation claims;

determining significant characteristics of each of said active claims;

applying said statistical models stored in said second data storage area to said significant characteristics of each of said active claims to formulate an individual cost prediction for each particular active claim;

calculating an individual reserve amount for each particular active claim based on the individual cost prediction for each particular active claim; and

placing money in a loss reserve account based on said calculated individual reserve amount for each particular active claim to fund future losses incurred on said particular active claim.

5. The method of claim 4, wherein said historical claim data is collated for claims over a period of years and wherein said step of applying said statistical models includes the steps of:

calculating a cost prediction for an active claim, said cost prediction representing the predicted cost of said claim in currency valued in a first year of said period; and

inflating said cost prediction to currency valued in a current year.

6. The method of claim 4, wherein said step of applying said statistical models to said active claims includes the steps of:

determining for a claim whether said claim is new, or whether said claim is old and a significant characteristic has changed since the last model review of said claim wherein a significant characteristic is a claim characteristic which has been determined during said model generation step to be significant in affecting claim cost and duration; and

applying a model to said claim to obtain a cost and duration prediction for said claim if said claim is new or if said claim is old and a significant characteristic has changed.

7. The method of claim 4, further including the steps of:

selecting a reserve adjustment factor for a claim or for a group of claims, wherein said reserve adjustment factor is a value used to adjust computer reserves upward or downward; and

adjusting computer reserves using said reserve adjustment factor.

8. The method of claim 4, further including the steps of:

applying said models stored in said second data storage area to said claims to obtain a total cost incurred prediction for each claim; and

proportioning said total cost incurred prediction for each claim among predefined cost categories, wherein said cost categories represent different types of costs commonly incurred on workers'"'"' compensation claims.

9. A method for accurately predicting future losses to be incurred by an insurance carrier on insurance claims on a claim by claim basis, said method comprising the steps of:

storing historical workers'"'"' compensation claim data in a first data storage area;

sorting said historical workers'"'"' compensation claim data into data subsets, wherein each data subset comprises claims of a predefined type and wherein each claim is placed into only one data subset and storing said data subsets in a second data storage area;

retrieving said data subsets from said second data storage area and generating a statistical model for each of said data subsets, said statistical model for each subset stored in a respective portion of a third data storage area, wherein each model represents the costs incurred on claims of said predefined type, and wherein the step of generating each model further comprises the steps of;

storing information regarding active insurance claims including selected claim characteristics which are significant in affecting the costs incurred on said claims in said subject data subset;

calculating and storing an intercept value which is a base statistical norm for the cost of said claims in said subject data subset;

calculating and storing an intercept modifier for each significant characteristic wherein said intercept modifier is a value which represents a statistical cost difference between all claims in said subject data subject and those claims in said data subset having said significant characteristic;

providing said significant characteristics of each of said insurance carriers'"'"'s active workers'"'"' compensation claims as input data to said statistical models retrieved from said portions of said third data storage area to obtain an individual reserve amount for each particular active claim; and

placing money in a loss reserve account based on said individual reserve amount for each particular active claim.

10. The method of claim 9, wherein said predefined types include:

claims wherein only medical expenses were incurred;

claims wherein a temporary disability to an injured claimant resulted; and

claims wherein a permanent disability to an injured claimant resulted.

11. The method of claim 9, wherein said step of collating historical claim data includes the steps of:

placing historical workers'"'"' compensation claim data into a carrier data file; and

loading said carrier data file onto a system computer which is used to generate said statistical models.

12. The method of claim 11 further including a step of cleansing said data of recognizable data errors.

13. The method of claim 9, wherein said step of sorting said historical claim data into data subsets includes a step of separating a portion of said historical claim data into model accuracy assessment data groups corresponding to each of said data subsets, said accuracy assessment data groups being used after generation of said models to test the accuracy of said models.

14. The method of claim 9, wherein each of said intercept values is the average cost of said claims in said subject data subset.

15. The method of claim 9, wherein said significant characteristics includes combinations of claim characteristics which are significant in affecting incurred costs on claims in a subject data subset.