Explainable machine learning models for Medicare fraud detection

Journal of Big Data

Table 7 Mean AUPRC values by classifier and number of features for ten iterations of fivefold cross validation, for classifying the Medicare Part D data (Part 1)

Features classifier	7a	7b	8	9	10
CatBoost	0.7575	0.7582	0.7570	0.7558	0.7585
ET	0.5941	0.5171	0.5585	0.6006	0.5878
LightGBM	0.4548	0.4533	0.4689	0.5116	0.5529
Logistic Regression	0.3468	0.3368	0.3497	0.3482	0.3537
Random Forest	0.5873	0.4937	0.5927	0.5393	0.5903
XGBoost	0.7533	0.7539	0.7533	0.7514	0.7571