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

EPJ Data Science

Table 15 Complete set of results with a radius set to 50 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	28,919	0.223	-	22,504	0.15	-	31,511	0.138	-
XGBoost †	28,001	0.229	I	20,858	0.15	I	33,215.9	0.147	I
XGBoost †	30,694.4	0.241	II	22,179.5	0.16	II	33,146.6	0.143	II
XGBoost †	28,753.3	0.222	III	21,009.4	0.157	III	31,370	0.132	III
XGBoost †	28,873.4	0.241	IV	22,577.1	0.15	IV	33,255.8	0.147	IV
LGBM	32,572	0.258	-	21,618	0.158	-	32,752	0.151	-
LGBM †	30,956.4	0.252	I	22,384.6	0.17	I	30,774.6	0.14	I
LGBM †	31,171.7	0.249	II	24,053.8	0.165	II	32,324	0.138	II
LGBM †	30,216	0.241	III	23,651.4	0.175	III	29,872	0.13	III
LGBM †	31,687.7	0.264	IV	22,408	0.161	IV	30,624.6	0.138	IV
RF	31,785	0.256	-	24,224	0.182	-	38,886	0.165	-
RF †	31,944.6	0.257	I	24,028	0.183	I	40,999.5	0.173	I
RF †	31,380	0.254	II	24,875.3	0.187	II	41,596.8	0.179	II
RF †	31,691	0.268	III	24,718.8	0.183	III	41,719	0.177	III
RF †	32,528.9	0.268	IV	24,885.7	0.184	IV	39,626	0.168	IV
DT	35,319	0.279	-	33,561	0.27	-	48,802	0.209	-
DT †	35,866.8	0.281	I	31,669	0.215	I	57,638.8	0.247	I
DT †	36,438.4	0.279	II	31,539.9	0.21	II	50,290	0.209	II
DT †	35,453	0.271	III	27,756	0.191	III	54,599.1	0.225	III
DT †	35,976.7	0.28	IV	34,275.4	0.274	IV	55,202.1	0.243	IV