A genetic algorithm based framework for software effort prediction

Journal of Software Engineering Research and Development

Table 16 Best learning schemes models performance (Continued)

DS	C	LS	S	MMRE	MdMRE	MMAR	MdMAR	MSA	MdSA	Pred25
7	3	6X5X6	0.79	0.61	0.72	2,206	902	58.25	80.14	0.35
7	4	6X4X6	0.79	0.61	0.72	2,360	894	55.34	80.20	0.35
7	5	6X2X3	0.77	0.84	0.92	2,612	1,238	50.58	72.58	0.28
7	5	6X3X3	0.77	0.86	0.94	2,625	1,259	50.33	72.15	0.27
7	6	6X2X3	0.77	0.84	0.92	2,612	1,238	50.58	72.58	0.28
7	6	6X3X3	0.77	0.86	0.94	2,625	1,259	50.33	72.15	0.27
7	7	6X4X6	0.79	0.61	0.72	2,360	894	55.34	80.20	0.35
7	8	1X3X14	0.77	0.71	0.84	2,655	1,047	49.76	76.19	0.31
7	8	6X2X14	0.78	0.73	0.87	2,674	1,110	49.40	75.31	0.29
7	9	1X3X14	0.77	0.71	0.84	2,655	1,047	49.76	76.19	0.31
7	9	6X2X14	0.78	0.73	0.87	2,674	1,110	49.40	75.31	0.29
8	1	2X3X1	0.73	0.76	0.87	2,691	1,117	49.08	74.22	0.28
8	2	1X5X3	0.69	0.94	1.01	2,941	1,406	44.34	69.05	0.25
8	3	2X4X1	0.73	0.74	0.85	2,563	1,084	51.50	75.00	0.29
8	3	2X5X1	0.73	0.73	0.85	2,549	1,075	51.76	75.35	0.29
8	4	1X5X3	0.69	0.94	1.01	2,941	1,406	44.34	69.05	0.25
8	5	2X1X1	0.74	0.73	0.85	2,558	1,084	51.60	75.20	0.29
8	5	2X5X1	0.73	0.74	0.87	2,570	1,112	51.37	74.66	0.29
8	6	2X4X1	0.73	0.73	0.85	2,577	1,100	51.23	74.76	0.29
8	6	2X5X1	0.73	0.73	0.86	2,591	1,115	50.98	74.41	0.29
8	7	1X5X3	0.69	0.94	1.01	2,941	1,406	44.34	69.05	0.25
8	8	2X2X6	0.75	0.81	0.89	2,547	1,144	51.80	74.77	0.30
8	9	2X3X1	0.73	0.74	0.87	2,643	1,091	50.00	74.58	0.28
8	9	2X5X1	0.74	0.74	0.86	2,631	1,085	50.21	74.91	0.29