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

Table 16

F-measure analysis by each TF-ML technique on individual dataset.

Technique	AR1	AR3	CM1	KC2	KC3	MW1	PC1	PC2	PC3	PC4
CDT	0.9614	0.9322	0.9438	0.8959	0.2857	0.9597	0.9658	0.9979	0.9427	0.4514
CS-Forest	0.9174	0.9074	0.9003	0.8575	?	0.9364	0.9522	0.9976	0.9115	0.198
DS	0.9524	0.9474	0.9483	0.8685	0.4262	0.9525	0.964	0.9979	0.9461	?
Forest-PA	0.9569	0.9391	0.9471	0.9011	?	0.9587	0.9662	0.9979	0.9455	0.4314
HT	0.9614	0.9091	0.9483	0.8994	?	0.96	0.964	0.9979	0.9461	0.0645
J48	0.9469	0.9273	0.9355	0.8847	0.375	0.9581	0.9649	0.9979	0.9396	0.5753
LMT	0.9569	0.9298	0.9426	0.9064	0.3103	0.9635	0.9605	0.9978	0.9424	0.4758
RF	0.9478	0.955	0.9423	0.8982	0.2174	0.958	0.9667	0.9979	0.9471	0.5108
RT	0.9422	0.9273	0.9064	0.8821	0.1972	0.9266	0.952	0.996	0.9197	0.4489
REP-T	0.9614	0.931	0.9427	0.8899	0.2308	0.9558	0.9663	0.9979	0.9451	0.4932