Simultaneous Incomplete Traffic Data Imputation and Similarity Pattern Discovery with Bayesian Nonparametric Tensor Decomposition

Table 2

Comparison of BNPTD with other baselines in the continuous missing scenario (the numbers 10, 20, 30 after the two methods denote CP rank and the best models are highlighted in bold).

Method	10%		20%		30%		40%		50%
	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE
BTD (10)	60.92	36.73	59.67	35.76	65.79	38.38	69.10	39.76	69.71	40.03
BNPTD (10)	60.19	35.66	59.10	35.07	65.01	37.70	66.76	38.18	66.08	37.56
GAIN	59.29	36.88	58.33	36.08	64.59	38.94	68.02	40.76	68.97	41.36
BTD (20)	49.85	30.70	51.29	30.74	52.22	30.97	57.62	32.74	53.77	31.35
BNPTD (20)	49.26	29.81	50.80	30.14	51.60	30.41	55.67	31.44	50.97	29.42
GAIN	48.69	31.01	50.04	31.11	51.18	31.52	56.46	33.56	53.06	32.39
BTD (30)	49.29	30.60	50.70	30.87	52.08	31.35	53.78	31.94	58.05	34.02
BNPTD (30)	48.71	29.71	50.21	30.27	51.46	30.79	51.96	30.67	5.02	31.92
GAIN	48.77	31.31	50.42	31.71	52.01	32.48	54.22	33.73	58.41	36.00
DA	73.36	43.89	71.81	42.61	78.36	45.15	80.93	46.12	80.67	45.95