A New High Order Fuzzy ARMA Time Series Forecasting Method by Using Neural Networks to Define Fuzzy Relations

Table 5

Data set 2 forecasts and forecasting performances for the best results of the methods with the sample size 7 for the test data.

Date	IMKB	Song-Chissom method [1]	Chen method [5]	Chen method [14]	Huarng distribution-based method [6]	Huarng average-based method [6]	Huarng ratio-based method [8]	Aladag et al. method [18]	Cheng et al. method [9]	Yolcu et al. method [25]	^*Proposed method
23.12.2009	51162	51139	51950	51350	50400	51500	51617,3	51200	50872	51317	51000
24.12.2009	51461	51139	51050	51150	50400	50550	50749,8	51200	50763	51317	51400
25.12.2009	51661	51139	51050	51450	50400	51500	51617,3	51200	50763	51317	51800
28.12.2009	51619	51139	51950	51650	52000	51700	51617,3	51200	50763	51317	51400
29.12.2009	51786	51139	51950	51750	52000	51700	51617,3	52000	50763	51317	51800
30.12.2009	51668	51139	51950	51850	52000	51700	51617,3	51200	50763	51317	51400
31.12.2009	52825	51139	51950	51950	52000	51700	51617,3	52000	50763	51317	52600
RMSE		769,80	553,53	373,71	781,78	567,03	561,19	447,71	1084,21	640,41	177,24
MAPE		0,0115	0,0096	0,0050	0,0134	0,0075	0,0072	0,0074	0,0185	0,0090	0,0030
DA		0,3333	0,3333	0,5000	0,3333	0,6667	0,5000	0,8333	0,3333	0,5000	1,0000

^*The best result.