Investigating Tree Family Machine Learning Techniques for a Predictive System to Unveil Software Defects

Table 7

False-positive rate analysis by each TF-ML technique on individual dataset.

Technique	AR1	AR3	CM1	KC2	KC3	MW1	PC1	PC2	PC3	PC4
CDT	0.926	0.873	0.902	0.439	0.663	0.834	0.69	0.996	0.871	0.562
CS-Forest	0.625	0.45	0.583	0.206	0.814	0.631	0.523	0.953	0.355	0.78
DS	0.927	0.548	0.902	0.337	0.534	0.747	0.931	0.996	0.898	0.878
Forest-PA	0.926	0.657	0.902	0.479	0.818	0.923	0.822	0.996	0.97	0.609
HT	0.926	0.557	0.902	0.466	0.816	0.923	0.931	0.996	0.898	0.849
J48	0.723	0.446	0.849	0.422	0.562	0.775	0.714	0.996	0.649	0.368
LMT	0.926	0.659	0.885	0.484	0.626	0.775	0.895	0.996	0.882	0.565
RF	0.928	0.332	0.848	0.431	0.707	0.746	0.654	0.996	0.731	0.531
RT	0.724	0.446	0.673	0.459	0.689	0.691	0.584	0.953	0.664	0.497
REP-T	0.926	0.766	0.903	0.526	0.69	0.894	0.69	0.996	0.859	0.522