A Price Prediction Method Based on CatBoost

Abstract

We have studied a price prediction method based on CatBoost, which can evaluate and predict the value of objects. In our approach, we applied many advanced and popular techniques of feature engineering. Also, we compared and analyzed different models, including linear models, tree-based models, and deep learning in the modelling part. Specifically, we have applied it to the housing price prediction, which has verified the effectiveness of our method. Our method can not only be used to predict housing prices, but also to evaluate or predict the value of other objects, such as cultural objects or artworks.