A Novel Fuzzy Time Series Forecasting Model Based on Multiple Linear Regression and Time Series Clustering

Table 2

Comparison of RMSEs and average RMSEs for different FTS methods for forecasting the TAIEX from 1990 to 1999.

Models	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	Average
Conventional model [4]
Average-based lengths	220	80	60	110	112	79	54	148	167	149	117.9
Distribution-based lengths	270	79	60	105	132	79	52	149	159	159	124.4
Weighted model [4]
Average-based lengths	227	61	67	105	135	70	54	133	151	142	114.5
Distribution-based lengths	266	67	56	105	114	70	52	152	154	145	118.1
Chen and Chen’s model [5]
Use Dow Jones	172.89	72.87	43.44	103.21	78.63	66.66	59.75	139.68	124.44	114.47	97.70
Use NASDAQ	169.93	66.12	49.61	104.75	75.66	67.01	60.90	140.86	144.13	119.32	99.83
Use Dow Jones and NASDAQ	172.99	74.85	43.78	101.38	78.13	68.14	61.26	139.29	132.94	116.64	98.94
Chen’s model [7]
Use Dow Jones	175.67	43.31	42.82	104.34	94.72	54.00	50.47	138.31	120.00	99.87	92.31
Use NASDAQ	176.60	43.73	42.42	104.18	95.04	54.49	49.84	139.85	119.22	102.60	92.80
Use Dow Jones and NASDAQ	174.62	43.22	42.66	104.17	94.60	54.24	50.50	138.51	117.87	101.33	92.17
Chen’s model [8]
Use Dow Jones	174.35	43.78	43.12	108.02	88.32	53.69	51.02	139.86	113.58	102.34	91.81
Use NASDAQ	176.17	43.16	43.34	106.66	87.95	53.30	51.10	138.41	113.88	102.11	91.61
Chen’s model [6]
Use Dow Jones	180.36	43.80	43.06	104.89	75.35	55.06	50.06	133.82	112.11	103.90	90.24
Use NASDAQ	174.15	45.04	42.10	104.94	76.40	54.96	50.17	133.45	113.37	104.99	89.96
Cai’s model [10]	187.10	39.58	39.37	101.80	76.32	56.05	49.45	123.86	118.41	102.34	89.44
Cheng’s model [12]	168.77	46.63	44.53	105.30	77.17	50.34	53.19	131.45	115.89	100.74	89.40
The proposed model	71.73	29.09	20.18	45.55	51.99	29.60	30.15	56.88	53.04	40.91	42.91