Application of Support Vector Regression in Indonesian Stock Price Prediction with Feature Selection Using Particle Swarm Optimisation

Table 2

PSO-SVR NMSE values of JKSE.

		Features
		11	12	13	14
Data training	40%	0.0010	0.0010	0.0009	0.0008
	50%	0.0008	0.0007	0.0007	0.0006
	60%	0.0006	0.0005	0.0005	0.0005
	70%	0.0007	0.0004	0.0004	0.0004
	80%	0.0010	0.0007	0.0006	0.0005
	90%	0.0061	0.0046	0.0046	0.0045