Spatio-Temporal Segmented Traffic Flow Prediction with ANPRS Data Based on Improved XGBoost

Table 4

Up-direction-related XGBoost models’ prediction results.

Methods	Error	Road 1	Road 2	Road 3	Road 4	Road 5	Road 6	Road 7
XGBoost-I	RMSE	33.6726	17.5608	20.2317	25.0574	19.4625	20.8586	29.1977
	MAE	23.8850	13.0644	15.1233	18.3011	14.4374	14.0289	19.9576
	MAPE	13.9770	12.1249	13.7570	10.8040	12.2136	12.0916	14.6106
XGBoost-I-lag	RMSE	31.8362	16.6891	19.9832	26.2245	18.7313	19.9094	30.4392
	MAE	21.9729	12.2463	14.5271	18.4053	14.2437	13.6255	20.6569
	MAPE	13.2454	11.5523	13.4027	10.9286	12.0946	12.5402	15.2520
XGBoost-S	RMSE	34.5123	18.3918	22.1078	26.1455	21.2394	21.7922	29.5969
	MAE	24.1088	13.3061	15.4927	18.4941	15.0558	14.1222	19.6536
	MAPE	14.1671	12.1188	13.7593	10.8694	12.6695	15.9026	14.4065
XGBoost-S-lag	RMSE	32.2435	17.2803	20.9974	26.6617	20.2683	21.0335	31.4545
	MAE	22.2236	12.4192	14.5295	18.5168	14.4424	13.7168	20.8345
	MAPE	13.5993	11.5780	13.2273	11.1660	12.5718	13.7145	15.4466