Insurance classification plan loss control system

• US 5,893,072 A
• Filed: 06/20/1996
• Issued: 04/06/1999
• Est. Priority Date: 06/20/1996
• Status: Expired due to Fees

• Current Assignee: Aetna Life & Casualty Co. (CVS Health Corporation)
• Original Assignee: Aetna Life & Casualty Co. (CVS Health Corporation)
• Inventors: Zizzamia, Frank M.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): Irshadullah, M.
• Application Number:
  US08/665,663
• Time in Patent Office: 1,020 Days
• Field of Search: 705/4, 705/5
• US Class Current: 705/4
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A loss control system for an insurance classification plan has a policy holder database, a predictive apparatus and a derived actual loss ratio generator. The policy holder database generates signals indicative of the premium, actual loss, a one a plurality of classification plan variable values and an actual loss ratio for each policy holder. The predictive apparatus generates a plurality of predicted loss ratio signals indicative of predicted loss ratios of the policy holders. The derived actual loss ratio generator generates signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of the policy holders.

Claims

1. A loss control system for an insurance classification plan for more accurately setting premium rates by more precisely determining expected losses, the insurance classification plan having a classification plan variable which represents an attribute of plurality of policy holders, the classification plan variable having a plurality of classification plan variable values, wherein each of the policy holders has a premium, an actual loss, a one the plurality of classification plan variable values, and an actual loss ratio,

which actual loss ratio is a ratio of the actual loss to the premium, the system comprising:

a policy holder database for generating a plurality of classification plan variable value signals, wherein each of the classification plan variable value signals is indicative of said classification plan variable value of a policy holder of the plurality of policy holders, and further for generating a plurality of actual loss signals, wherein each of the actual loss signals is indicative of the actual loss of a policy holder of the plurality of policy holders, and further for generating a plurality of premium signals, wherein each premium signal in the plurality of premium signals is indicative of the premium of a policy holder of the plurality of policy holders, and further for generating a plurality of actual loss ratio signals, wherein each of the actual loss ratio signals is indicative of the actual loss ratio of a policy holder of the plurality of policy holders;

predictive means for receiving said plurality of classification plan variable value signals and for receiving said actual loss ratio signals, and further for generating in dependence thereupon a plurality of predicted loss ratio signals, wherein each of the predicted loss ratio signals is indicative of a predicted loss ratio of a policy holder of the plurality of policy holders;

derived actual loss ratio generator means for receiving said plurality of classification plan variable value signals, said actual loss ratio signals and said predicted loss ratio signals, and further for generating in dependence thereupon derived actual loss ratio signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of a policy holder of the plurality of policy holders; and

whereby said derived actual loss ratio signals are used to determine premium pricing effectiveness.

2. The loss control system of claim 1, further comprising:

a relativity database for generating a first set of relativity signals which are indicative of a plurality of relativity values, each relativity value of the plurality of relativity values having a one-to-one correspondence with a one of the plurality of classification plan variable values, wherein each relativity value of said plurality of relativity values represents a relationship between an expected loss and said classification plan variable value; and

relativity adjuster means for receiving said plurality of classification plan variable signals, said actual loss ratio signals, said predicted loss ratio signals and said first set of relativity signals, and further for generating in dependence thereupon relativity adjustment signals which are indicative of prescribed adjustments to said first set of relativity signals; and

wherein

said relativity database further receives said relativity adjustment signals and generates in dependence thereupon a second set of relativity signals which are indicative of a plurality of relativity values which are adjusted in accordance with prescribed adjustments, said adjustment signals increasing or decreasing said second set of relativity values in dependence upon said relativity signals of succeeding classification plan variable value signals.

3. The loss control system of claim 1, further comprising a graphical user interface means for generating graphical signals in dependence on received display signals, wherein said graphical signals are indicative of images and text which are displayed to a user in graphical form and wherein said display signals are indicative of commands to display prescribed images and text to a user, said graphical user interface means further for receiving from the user input signals which are indicative of user input commands and for generating user command signals in dependence on said input signals, which user command signals control said policy holder database, said predictive means, and said derived actual loss ratio generator means in accordance with a prescribed process.

4. The loss control system of claim 1, wherein said derived actual loss ratio generator means comprises:

bin generator means for receiving said plurality of classification plan variable value signals, said actual loss ratio signals and said predicted loss ratio signals, and further for generating in dependence thereupon bin signals which are indicative of a plurality of bins, wherein each bin is indicative of a set of policy holders who have a predicted loss ratio within a prescribed range.

5. The loss control system of claim 4, wherein said derived actual loss ratio generator means further comprises:

group generator means for receiving said bin signals, and further for generating in dependence thereupon bin actual loss ratio signals, wherein each bin actual loss ratio signal is indicative of a sum of all actual losses of each policy holder of a bin divided by a sum of all premiums of each policy holder of a bin, and which group generator is further for generating, in dependence on said bin signals, trend line signals which are indicative of a best fit linear relationships among said bin actual loss ratio signals, and which group generator is further for generating, in dependence on said bin signals, group curve signals which are indicative of a plurality of groups, wherein each group is indicative of a prescribed set of bins.

6. The loss control system of claim 5, wherein said derived actual loss ratio generator means further comprises:

group curve generator means for receiving said trend line signals, and for generating in dependence thereupon group point signals which are indicative of group points, wherein each group point is indicative of a predicted loss ratio of policy holders of a bin and an actual loss ratio of policy holders of a bin, which group curve generator means is further for generating group curve signals which are indicative of a best fit curve through said group points.

7. A method of controlling loss for an insurance classification plan for setting premium rates which more precisely reflect expected losses, the insurance classification plan having a classification plan variable which represents an attribute of a plurality of policy holders, the classification plan variable having a plurality of classification plan variable values, wherein each of the policy holders has a premium, an actual loss, a one the plurality of classification plan variable values, and an actual loss ratio, which actual loss ratio is a ratio of the actual loss to the premium, the method comprising the steps of:

generating a plurality of classification plan variable value signals, wherein each of the classification plan variable value signals is indicative of said classification plan variable value of a policy holder of the plurality of policy holders;

generating a plurality of actual loss signals, wherein each of the actual loss signals is indicative of the actual loss of a policy holder of the plurality of policy holders;

generating a plurality of premium signals, wherein each premium signal in the plurality of premium signals is indicative of the premium of a policy holder of the plurality of policy holders;

generating a plurality of actual loss ratio signals, wherein each of the actual loss ratio signals is indicative of the actual loss ratio of a policy holder of the plurality of policy holders;

generating, in dependence upon said plurality of classification plan variable value signals and upon said actual loss ratio signals, a plurality of predicted loss ratio signals, wherein each of the predicted loss ratio signals is indicative of a predicted loss ratio of a policy holder of the plurality of policy holders; and

generating, in dependence upon said plurality of classification plan variable value signals, said actual loss ratio signals and said predicted loss ratio signals, derived actual loss ratio signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of a policy holder of the plurality of policy holders; and

whereby said derived actual loss ratio signals are used to determine premium pricing effectiveness.

8. The method of claim 7, further comprising the steps of:

generating a first set of relativity signals which are indicative of a plurality of relativity values, each relativity value of the plurality of relativity values having a one-to-one correspondence with a one of the plurality of classification plan variable values, wherein each said relativity value of said plurality of relativity values represents a relationship between an expected loss and said classification plan variable value;

generating, in dependence upon said plurality of classification plan variable value signals, said actual loss ratio signals, said predicted loss ratio signals and said first set of relativity signals, relativity adjustment signals which are indicative of prescribed adjustments to said first set of relativity signals;

generating in dependence upon said relativity adjustment signals, a second set of relativity signals which are indicative of a plurality of relativity values which are adjusted in accordance with said prescribed adjustments, said adjustment signals increasing or decreasing said second set of relativity values in dependence upon said relativity signals of succeeding classification plan variable value signals.

9. The method of claim 7, wherein the step of generating derived actual loss ratio signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of a policy holder of the plurality of policy holders comprises the step of:

generating, in dependence upon said plurality of classification plan variable value signals, said actual loss ratio signals and said predicted loss ratio signals, bin signals which are indicative of a plurality of bins, wherein each bin is indicative of a set of policy holders who have a predicted loss ration within a prescribed range.

10. The method of claim 9, wherein the step of generating derived actual loss ratio signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of a policy holder of the plurality of policy holders comprises the steps of:

generating, in dependence upon said bin signals, bin actual loss ratio signals, wherein each bin actual loss ratio signal is indicative of a sum of all actual losses of each policy holder of a bin divided by a sum of all premiums of each policy holder of a bin;

generating, in dependence on said bin signals, trend line signals which are indicative of a best fit linear relationships among said bin actual loss ratio signals; and

generating, in dependence on said bin signals, group curve signals which are indicative of a plurality of groups, wherein each group is indicative of a prescribed set of bins.

11. The method of claim 10, wherein the step of generating derived actual loss ratio signals which are indicative of a difference between the predicted loss ratio and the actual loss ratio of a policy holder of the plurality of policy holders comprises the steps of:

generating, in dependence upon said trend line signals, group point signals which are indicative of group points, wherein each group point is indicative of a predicted loss ratio of policy holders of a bin and an actual loss ratio of policy holders of a bin; and

generating group curve signals which are indicative of a best fit curve through said group points.