Machine learning for inference: using gradient boosting decision tree to assess non-linear effects of bus rapid transit on house prices

The adoption of bus rapid transit (BRT) systems has gained worldwide popularity over the past several decades. China is no exception as it long been aiming at promoting public transportation. Prior studies have provided extensive evidence that BRT substantial effects on house prices with traditional econometric techniques, such hedonic pricing models. However, few those investigations discussed non-linear relationship between and prices. Using Xiamen data, this study employs a machine learning technique, namely gradient boosting decision tree (GBDT), to scrutinize This documents positive association accessibility stations negative proximity corridor Moreover, suggests indicates GBDT more predictive power than