System and method for automated establishment of experience ratings and/or risk reserves

• US 20060015373A1
• Filed: 09/10/2003
• Published: 01/19/2006
• Est. Priority Date: 09/10/2003
• Status: Abandoned Application

• Current Assignee: Swiss Reinsurance Company
• Original Assignee: Swiss Reinsurance Company
• Inventors: Cuypers, Frank
• Application Number:
  US10/531,459
• Publication Number:
  US 20060015373A1
• Time in Patent Office: Days
• US Class Current: 705/4
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

System and method for automated experience rating and/or loss reserving for events, a certain event P_i,f of an initial year i including development values P_ikf with development year k. For i, k applicable is i=1, . . . , K and k=1, . . . , K, K being the last known development year, and the first initial year i=1 comprising all development values P_1kf in a specified way. To determine the development values P_{i,K−(i−j)+1,f} neural networks N_i,j are generated iteratively for each initial year i (i−1), whereby j=1, . . . ,(i−1) are the number of iterations for a particular initial year i and whereby the neural network N_i,j+1 depends recursively on the neural network N_i,j. In particular the system and method is suitable for experience rating for insurance contracts and/or excess of loss reinsurance contracts.

Claims

1-23. -23. (canceled)

24. Computer-based system for automated experience rating and/or loss reserving, a certain event P_if of an initial time interval i including development values P_ikf of the development intervals k=1, . . . ,K, K being the last known development interval with i=1, . . . , K, and all development values P_1kf being known, characterized

in that the system for automated determination of the development values P_i,K+2−

i,f, . . . ,P_i,K,f comprises at least one neural network, the system for determination of the development values P<sub>i,K+2−

i,f</sub>, . . . ,P_i,K,f of an event P_i,f(i−

1) comprising iteratively generated neural networks N_ij for each initial time interval i with j=1, . . . ,(i−

1), and the neural network N_ij+1 depending recursively on the neural network N_ij.

25. Computer-based system according to claim 24, characterized in that for the events the initial time interval corresponds to an initial year, and the development intervals correspond to development years.

26. Computer-based system according to claim 24, characterized in that training values for weighting a particular neural network N_ij comprise the development values P_p,q,f with p=1, . . . ,(i−

1) and q=1, . . . ,K−

(i−

j).

27. Computer-based system according to claim 24, characterized in that the neural networks N_ij for the same j are identical, the neural network N_i+1,j=i being generated for an initial time interval i+1, and all other neural networks N_i+1,j<

i corresponding to networks of earlier initial time intervals.

28. Computer-based system according to claim 24, characterized in that the system further comprises events P_i,f with initial time interval i<

1, all development values P<sub>i<

1,k,f</sub> being known for the events P<sub>i<

1,f</sub>.

29. Computer-based system according to claim 24, characterized in that the system comprises at least one scaling factor by means of which the development values P_ikf of the different events P_i,f are scalable according to their initial time interval.

30. Computer-based method for automated experience rating and/or loss reserving, development values P_ikf with development intervals k=1, . . . , K being assigned to a certain event P_if of an initial time interval i, K being the last known development interval with i=1, . . . , K, and all development values P_1kf being known for the events P_1,f, characterized

in that at least one neural network is used for determination of the development values P_i,K+2−

i,f, . . . ,P_i,K,f, neural networks N_ij being generated iteratively (i−

1) for each initial time interval i with j=1, . . . ,(i−

1), for determination of the development values P<sub>i,K−

(i−

j)+1,f</sub>, and the neural network N_i,j+1 depending recursively on the neural network N_ij.

31. Computer-based method according to claim 30, characterized in that for the events the initial time interval is assigned to the initial year, and the development intervals are assigned to development years.

32. Computer-based method according to claim 30, characterized in that for weighting a particular neural network Ni,j, the development values P_p,q,f with p=1, . . . , (i−

1) and q=1, . . . , K−

(i−

j) are used.

33. Computer-based method according to claim 30, characterized in that the neural networks N_ij for same j are trained identically, the neural network N_i+1,j=i being generated for an initial time interval i+1, and all other neural networks N_i+1,j<

i of earlier initial time intervals being taken over.

34. Computer-based method according to claim 30, characterized in that used in addition for determination are events P_i,f with initial time interval i<

1, all development values P<sub>i<

1,k,f</sub> being known for the events P<sub>i<

1,f</sub>.

35. Computer-based method according to claim 30, characterized in that by means of at least one scaling factor the development values P_ikf of the different events P_i,f are scaled according to their initial time interval.

46. Computer program product which is loadable in the internal memory of a digital computer and comprises software code segments with which the steps according to claim 30 are able to be carried out when the product is running on a computer, the neural networks being able to be generated through software and/or hardware.

36. Computer-based method for automated experience rating and/or loss reserving, development values P_i,k,f with development intervals k=1, . . . , K being stored assigned to a certain event P_i,f of an initial time interval i, whereby i=1, . . . , K and K is the last known development interval, and whereby all development values P_1,k,f are known for the first initial time interval, characterized

in that, in a first step, for each initial time interval i=2, . . . ,K, by means of iterations j=1, . . . ,(i−

1), at each iteration j, a neural network N_ij is generated with an input layer with K−

(i−

j) input segments and an output layer, each input segment comprising at least one input neuron and being assigned to a development value P_i,k,f,

in that, in a second step, the neural network N_ij is weighted with the available events P_i,f of all initial time intervals m=1, . . . ,(i−

1) by means of the development values P<sub>m, . . . K−

(i−

j),f</sub> as input and P<sub>m,1 . . . K−

(i−

j)+1,f</sub> as output, and

in that, in a third step, by means of the neural network N_ij the output values O_i,f for all events P_i,f of the initial year i are determined, the output value O_i,f being assigned to the development value P<sub>i,K−

(i−

j)+1,f</sub> of the event P_i,f, and the neural network N_ij depending recursively on the neural network N_ij+1.

37. Computer-based method according to claim 36, characterized in that for the events the initial time interval is assigned to an initial year, and the development intervals are assigned to development years.

38. System of neural networks, which neural networks N_i each comprise an input layer with at least one input segment and an output layer, the input layer and output layer comprising a multiplicity of neurons which are connected to one another in a weighted way, characterized

in that the neural networks N_i are able to be generated iteratively using software and/or hardware by means of a data processing unit, a neural network N_i+1depending recursively on the neural network N_i, and each network N_i+1comprising in each case one input segment more than the network N_i,

in that, beginning at the neural network N_i, each neural network N_i is trainable by means of a minimization module by minimizing a locally propagated error, and

in that the recursive system of neural networks is trainable by means of a minimization module by minimizing a globally propagated error based on the local error of the neural network N_i.

39. System of neural networks according to claim 38, characterized in that the output layer of the neural network N_i is connected to at least one input segment of the input layer of the neural network N_i+1 in an assigned way.

40. Computer program product which comprises a computer-readable medium with computer program code means contained therein for control of one or more processors of a computer-based system for automated experience rating and/or loss reserving, development values P_i,k,f with development intervals k=1, . . . , K being stored assigned to a certain event P_i,f of an initial time interval i, whereby i=1, . . . , K, and K is the last known development interval, and all development values P_1,k,f being known for the first initial time interval i=1, characterized

in that by means of the computer program product at least one neural network is able to be generated using software and is usable for determination of the development values P_i,K+2−

i,f, . . . , P_i,K,f, whereby, for

determination of the development values P<sub>i,K−

(i−

j)+1,f</sub> neural networks N_ij are able to be generated for each initial time interval i by means of the computer program iteratively (i−

1) with j=1, . . . ,(i−

1), and whereby the neural network N_{i, ,j+1} depends recursively on the neural network N_ij.

41. Computer program product according to claim 40, characterized in that for the events the initial time interval is assigned to an initial year, and the development intervals are assigned to development years.

42. Computer program product according to claim 40, characterized in that for weighting a particular neural network N_ij by means of the computer program product the development values P_p,q,f with p=1, . . . ,(i−

1) and q=1, . . . ,K−

(i−

j) are readable from a database.

43. Computer program product according to claim 40, characterized in that with the computer program product the neural networks N_ij are trained identically for the same j, the neural network N_{i+1 J=i} being generated for an initial time interval i+1 by means of the computer program product, and all other neural networks N_i+1,j<

i of earlier initial intervals being taken over.

44. Computer program product according to claim 40, characterized in that the database additionally comprises in a stored way events P_i,f with initial time interval i<

1, all development values P<sub>i<

1,k,f</sub> being known for the events P<sub>i<

1,f</sub>.

45. Computer program product according to claim 40, characterized in that the computer program product comprises at least one scaling factor by means of which the development values P_ikf of the different events P_i,f are scalable according to their initial time interval.