A comprehensive evaluation of ensemble learning for stock-market prediction

Nti, Isaac Kofi; Adekoya, Adebayo Felix; Weyori, Benjamin Asubam

doi:10.1186/s40537-020-00299-5

Journal of Big Data

Table 17 Bagging and boosting ensemble regressors error metrics result over GSE dataset

From: A comprehensive evaluation of ensemble learning for stock-market prediction

Models	No. of estimators	RMSE	MAE	R²	EVS	MedAE	RMSLE	Train time	Test time
DTBagr	1	0.002	0.001	0.961	0.961	0.001	0.002	0.006	0.002
SVMBagr	1	0.010	0.008	− 0.217	0.000	0.009	0.009	0.005	0.001
MLPBagr	1	0.011	0.009	− 0.713	− 0.669	0.009	0.011	0.242	0.014
DTBotr	1	0.003	0.002	0.882	0.882	0.002	0.003	0.004	0.001
SVMBotr	1	0.010	0.008	− 0.217	0.000	0.009	0.009	0.005	0.001
MLPBotr	1	0.010	0.008	− 0.323	− 0.323	0.006	0.010	0.156	0.001
DTBagr	5	0.001	0.001	0.973	0.973	0.001	0.001	0.019	0.002
SVMBagr	5	0.010	0.008	− 0.217	0.000	0.009	0.009	0.022	0.002
MLPBagr	5	0.004	0.003	0.742	0.755	0.003	0.004	0.526	0.003
DTBotr	5	0.002	0.002	0.931	0.931	0.001	0.002	0.013	0.001
SVMBotr	5	0.010	0.008	− 0.217	0.000	0.009	0.009	0.144	0.011
MLPBotr	5	0.007	0.004	0.407	0.408	0.003	0.006	1.919	0.003
DTBagr	15	0.002	0.001	0.970	0.970	0.001	0.001	0.047	0.005
SVMBagr	15	0.010	0.008	− 0.216	0.000	0.009	0.009	0.045	0.005
MLPBagr	15	0.003	0.002	0.887	0.895	0.002	0.003	1.531	0.008
DTBotr	15	0.001	0.001	0.980	0.980	0.001	0.001	0.075	0.022
SVMBotr	15	0.010	0.008	− 0.217	0.000	0.009	0.009	0.171	0.013
MLPBotr	15	0.004	0.003	0.825	0.829	0.002	0.004	2.223	0.005
DTBagr	20	0.001	0.001	0.975	0.975	0.975	0.001	0.041	0.004
SVMBagr	20	0.010	0.008	− 0.220	0.000	0.220	0.009	0.029	0.005
MLPBagr	20	0.002	0.001	0.963	0.977	0.963	0.002	2.427	0.008
DTBotr	20	0.001	0.001	0.980	0.980	0.980	0.001	0.048	0.004
SVMBotr	20	0.010	0.008	− 0.217	0.000	0.217	0.009	0.046	0.005
MLPBotr	20	0.003	0.002	0.861	0.870	0.861	0.003	2.921	0.040
DTBagr	50	0.001	0.001	0.977	0.977	0.001	0.001	0.317	0.076
SVMBagr	50	0.010	0.008	− 0.216	0.000	0.009	0.009	0.376	0.171
MLPBagr	50	0.001	0.001	0.982	0.990	0.001	0.001	8.220	0.029
DTBotr	50	0.001	0.001	0.987	0.987	0.001	0.001	0.106	0.009
SVMBotr	50	0.010	0.008	− 0.217	0.000	0.009	0.009	0.098	0.015
MLPBotr	50	0.002	0.001	0.958	0.965	0.001	0.002	7.231	0.023
DTBagr	100	0.001	0.001	0.975	0.975	0.001	0.001	0.182	0.028
SVMBagr	100	0.010	0.008	− 0.215	0.000	0.009	0.009	0.251	0.039
MLPBagr	100	0.001	0.001	0.991	0.994	0.001	0.001	15.411	0.054
DTBotr	100	0.001	0.001	0.991	0.991	0.001	0.001	0.644	0.025
SVMBotr	100	0.010	0.008	− 0.217	0.000	0.009	0.009	0.214	0.092
MLPBotr	100	0.001	0.001	0.983	0.987	0.001	0.001	14.632	0.045
DTBagr	150	0.001	0.001	0.976	0.976	0.001	0.001	0.266	0.027
SVMBagr	150	0.010	0.008	− 0.212	0.000	0.009	0.009	0.181	0.073
MLPBagr	150	0.001	0.001	0.994	0.997	0.001	0.001	20.029	0.206
DTBotr	150	0.001	0.001	0.994	0.994	0.000	0.001	0.381	0.023
SVMBotr	150	0.010	0.008	− 0.217	0.000	0.009	0.009	0.249	0.032
MLPBotr	150	0.001	0.001	0.985	0.989	0.001	0.001	19.393	0.042
DTBagr	200	0.001	0.001	0.974	0.974	0.001	0.001	0.393	0.032
SVMBagr	200	0.010	0.008	− 0.213	0.000	0.009	0.009	0.256	0.048
MLPBagr	200	0.001	0.001	0.995	0.996	0.001	0.001	28.065	0.238
DTBotr	200	0.001	0.001	0.995	0.995	0.000	0.001	0.786	0.024
SVMBotr	200	0.010	0.008	− 0.217	0.000	0.009	0.009	0.474	0.038
MLPBotr	200	0.001	0.001	0.985	0.989	0.001	0.001	26.815	0.048

Back to article page