Anomaly Detection in Health Insurance Claims Using Bayesian Quantile Regression

Table 6

Claims and their probabilities of being anomalous.

	Claim amount
[36]	9440	2.67E − 15	0.000233	1
[103]	9638	3.17E − 11	0.00063	1
[45]	9316	1.24E − 10	0.000735	0.999999
[8]	8941	2.95E − 09	0.001063	0.999982
[89]	9117	3.30E − 09	0.001078	0.999981
[83]	9241	3.65E − 09	0.001091	0.999979
[6]	9024	1.55E − 08	0.001301	0.999924
[12]	9937	4.02E − 08	0.001465	0.999826
[4]	9284	8.22E − 08	0.001604	0.999675
[92]	9855	2.92E − 07	0.00189	0.999019
[41]	6661	0.407214	0.030185	0.011533
[93]	6624	0.935536	0.066375	0.011045
[82]	12272	0.466905	0.032471	0.010828
[55]	7356	0.523207	0.034726	0.010339
[75]	9562.8	0.885195	0.05808	0.010222
[90]	6115	0.881762	0.057646	0.010186
[80]	7939	0.878415	0.057234	0.010152
[1]	7257	0.599579	0.038033	0.009886
[24]	6522	0.62609	0.039274	0.009777
[70]	9712.3	0.811345	0.050588	0.009719
[16]	7471	0.651635	0.040528	0.009695
[61]	10472.8	0.80352	0.049954	0.009691
[50]	7206	0.675306	0.04175	0.009638
[97]	11065.6	0.781346	0.04827	0.009631
[47]	6831	0.687836	0.042424	0.009615