Does noise affect housing prices? A case study in the urban area of Thessaloniki

EPJ Data Science

Table 14 Complete set of results with a radius set to 100 m using 5-fold cross-validation for areas A, B and C. The results are presented in terms of the mean absolute error (MAE) and mean absolute percentage error (MAPE). Bold text marks the best score across all models for a given area. The dagger symbol indicates that noise pollution was included in the experiment. The “Noise” column refers to the different noise characteristics: one feature for the average day noise and one for the average night noise (I), one feature which averages both day and night noise (II), one feature for the average day noise (III), one feature for the average night noise (IV) and no features for noise in the baseline model (-)

Model	A			B			C
Model	MAE	MAPE	Noise	MAE	MAPE	Noise	MAE	MAPE	Noise
XGBoost	28919	0.223	-	22504	0.15	-	31,511	0.138	-
XGBoost †	29,698.5	0.241	I	19,189	0.144	I	30,749.4	0.136	I
XGBoost †	28,888	0.233	II	20,605	0.147	II	33,436.3	0.143	II
XGBoost †	28,735.5	0.236	III	21,040.7	0.152	III	30,185.5	0.134	III
XGBoost †	29,662.7	0.235	IV	19,762.4	0.146	IV	30,141	0.128	IV
LGBM	32,572	0.258	-	21,618	0.158	-	32,752	0.151	-
LGBM †	31,629.7	0.266	I	23,702	0.183	I	31,812.2	0.138	I
LGBM †	31,477	0.258	II	22,715	0.173	II	31,448.3	0.143	II
LGBM †	32,180.6	0.263	III	23,218.7	0.175	III	33,286.6	0.145	III
LGBM †	31,423.7	0.272	IV	25,358.3	0.199	IV	31,139	0.138	IV
RF	32,519	0.267	-	24,259	0.181	-	38,922	0.1655	-
RF †	32,383	0.262	I	25,574.9	0.186	I	41,436.5	0.174	I
RF †	31,759	0.259	II	24,481	0.182	II	40,389	0.173	II
RF †	32,054.2	0.264	III	24,698.3	0.185	III	40,335.9	0.175	III
RF †	31,863.9	0.269	IV	24,868.8	0.196	IV	42,175.9	0.182	IV
DT	35,264	0.277	-	28,966	0.238	-	48,802	0.209	-
DT †	36,449.4	0.284	I	30,932.4	0.26	I	54,755.2	0.234	I
DT †	31,771.3	0.271	II	30,671	0.25	II	52,368.8	0.226	II
DT †	31,771	0.271	III	31,862.5	0.212	III	52,077	0.225	III
DT †	36,316.5	0.284	IV	31,694.2	0.264	IV	52,355	0.226	IV