System and process for a fusion classification for insurance underwriting suitable for use by an automated system
First Claim
1. A computer implemented system for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the system comprising:
- a plurality of decision engines where each decision engine performs processing to output a result, wherein each output result comprises a classification for the insurance application, and the processing performed by the decision engine is based on factors derived from the insurance application such as risk of mortality;
a fusion engine, where the fusion engine;
compares the output results of the plurality of decision engines; and
fuses the plurality of output results into a single fused decision;
a measurement engine for measuring at least a consensus of the fused decision;
an estimation engine to estimate the degree of confidence in the fused engine based on the measured consensus;
a production decision engine, where the production decision engine performs processing to generate a production decision engine output which comprises a classification for the insurance application; and
a comparison engine to generate a comparison output, where the comparison engine compares the production decision engine output with the fused decision, and outputs results of the comparison.
4 Assignments
0 Petitions
Accused Products
Abstract
A method and system for fusing a collection of classifiers used for an automated insurance underwriting system and/or its quality assurance is described. Specifically, the outputs of a collection of classifiers are fused. The fusion of the data will typically result in some amount of consensus and some amount of conflict among the classifiers. The consensus will be measured and used to estimate a degree of confidence in the fused decisions. Based on the decision and degree of confidence of the fusion and the decision and degree of confidence of the production decision engine, a comparison module may then be used to identify cases for audit, cases for augmenting the training/test sets for re-tuning production decision engine, cases for review, or may simply trigger a record of its occurrence for tracking purposes. The fusion can compensate for the potential correlation among the classifiers. The reliability of each classifier can be represented by a static or dynamic discounting factor, which will reflect the expected accuracy of the classifier. A static discounting factor is used to represent a prior expectation about the classifier'"'"'s reliability, e.g., it might be based on the average past accuracy of the model, while a dynamic discounting is used to represent a conditional assessment of the classifier'"'"'s reliability, e.g., whenever a classifier bases its output on an insufficient number of points it is not reliable.
304 Citations
51 Claims
-
1. A computer implemented system for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the system comprising:
-
a plurality of decision engines where each decision engine performs processing to output a result, wherein each output result comprises a classification for the insurance application, and the processing performed by the decision engine is based on factors derived from the insurance application such as risk of mortality; a fusion engine, where the fusion engine; compares the output results of the plurality of decision engines; and fuses the plurality of output results into a single fused decision; a measurement engine for measuring at least a consensus of the fused decision; an estimation engine to estimate the degree of confidence in the fused engine based on the measured consensus; a production decision engine, where the production decision engine performs processing to generate a production decision engine output which comprises a classification for the insurance application; and a comparison engine to generate a comparison output, where the comparison engine compares the production decision engine output with the fused decision, and outputs results of the comparison. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computer implemented system for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the system comprising:
-
a plurality of decision engines, where each decision engine generates an output result; a fusion engine, where the fusion engine; compares the output results of the plurality of decision engines; and fuses the plurality of output results into a single fused decision, where; a) the fused decision comprises a classification designation for the insurance application and a confidence measure; b) the fusion of the plurality of output results is an associative function; and c) the fusion of the output results is based at least in part on a correlation between the classification designations of each of the output results; a production decision engine, where the production decision engine generates a production output result which comprises a classification designation for the insurance application and a confidence measure; and a comparison engine to generate a comparison output for evaluating the insurance application and to the comparison output, where the comparison engine compares; a) the production output result classification assignment and the fused decision classification assignment; and b) the production output result confidence measure and the fused decision confidence measure. - View Dependent Claims (11, 12, 13)
-
-
14. A computer implemented process for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the process comprising:
-
generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine; comparing the plurality of decision output results; fusing the plurality of decision output results based at least in part on the comparison; measuring the fused decision for at least a consensus; estimating a degree of confidence in the fused decision based on the measured consensus; generating a production output result; comparing the production output result with the fused decision to generate a comparison output for evaluating the insurance application; outputting the comparison output; and performing a determination whether the application should be added to the plurality of previous insurance application underwriting decisions. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21)
-
-
22. A computer implemented process for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the process comprising:
-
generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine and the production output result comprises a classification designation for the insurance application and a confidence measure; comparing the plurality of decision output results; fusing the plurality of decision output results based at least in part on the comparison, where; a) the fused decision comprises a classification designation for the insurance application and a confidence measure; b) the fusion of the plurality of output results is an associative function; and c) the fusion of the decision output results is based at least in part on a correlation between the classification designations of each of the output results; generating a production output result; comparing the production output result with the fused decision, where the comparison of the production output result and the fused decision includes a comparison of; the production output result classification designation and the fused decision classification designation; and the production output result confidence measure and the fused decision confidence measure; and generating a compared result comprising a classification designation and a confidence measure; and outputting the compared result. - View Dependent Claims (23, 24, 25)
-
-
26. A computer implemented system for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the system comprising:
-
means for generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine; means for comparing the plurality of decision output results; means for fusing the plurality of decision output results based at least in part on the comparison; means for measuring the fused decision for at least a consensus; means for estimating a degree of confidence in the fused decision based on the measured consensus; means for generating a production output result; and means for comparing the production output result with the fused decision to generate a comparison output for evaluating the insurance application; and means for outputting the comparison output. - View Dependent Claims (27, 28, 29, 30, 31, 32, 33, 34)
-
-
35. A computer implemented system for underwriting an insurance application based on a plurality of previous insurance application underwriting decisions, the system comprising:
-
means for generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine and the production output result comprises a classification designation for the insurance application and a confidence measure; means for comparing the plurality of decision output results; means for fusing the plurality of decision output results based at least in part on the comparison, where; a) the fused decision comprises a classification designation for the insurance application and a confidence measure; b) the fusion of the plurality of output results is an associative function; and c) the fusion of the decision output results is based at least in part on a correlation between the classification designations of each of the output results; means for generating a production output result; means for comparing the production output result with the fused decision, where the comparison of the production output result and the fused decision includes a comparison of; the production output result classification designation and the fused decision classification designation; and the production output result confidence measure and the fused decision confidence measure; and means for generating a compared result comprising a classification designation and a confidence measure for evaluating the insurance application; and means for outputting the compared result. - View Dependent Claims (36, 37, 38)
-
-
39. A computer implemented computer readable medium having code for causing a processor to underwrite an insurance application based on a plurality of previous insurance application underwriting decisions, the medium comprising:
-
code for generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine; code for comparing the plurality of decision output results; code for fusing the plurality of decision output results based at least in part on the comparison; code for measuring the fused decision for at least a consensus; code for estimating a degree of confidence in the fused decision based on the measured consensus; code for generating a production output result; code for comparing the production output result with the fused decision to generate a comparison output for evaluating the insurance application; and code for outputting the comparison output. - View Dependent Claims (40, 41, 42, 43, 44, 45, 46, 47)
-
-
48. A computer readable medium having code for causing a process to underwrite an insurance application based on a plurality of previous insurance application underwriting decisions, the medium comprising:
-
code for previous insurance application underwriting decisions, the process comprising; code for generating a plurality of decision output results for the application, where each of the decision output results is generated by a separate decision engine and the production output result comprises a classification designation for the insurance application and a confidence measure; code for comparing the plurality of decision output results; code for fusing the plurality of decision output results based at least in part on the comparison, where; a) the fused decision comprises a classification designation for the insurance application and a confidence measure; b) the fusion of the plurality of output results is an associative function; and c) the fusion of the decision output results is based at least in part on a correlation between the classification designations of each of the output results; code for generating a production output result; code for comparing the production output result with the fused decision, where the comparison of the production output result and the fused decision includes a comparison of; the production output result classification designation and the fused decision classification designation; and the production output result confidence measure and the fused decision confidence measure; and code for generating a compared result comprising a classification designation and a confidence measure for evaluating the insurance application; and code for outputting the output result. - View Dependent Claims (49, 50, 51)
-
Specification