Monthly Housing Rent Forecast based on LightGBM (Light Gradient Boosting) Model

Jinze Li

College of Information Science and Engineering, Shandong Agricultural University, Tai’an, 271000, China

Abstract: In today's society, housing rent is determined by many factors such as decoration, location, type of house, convenience of transportation, market supply and demand, etc. For the relatively traditional industry of renting, the problem of serious information asymmetry has always existed. This study is based on the pain points of the rental market, based on real renting market data after desensitization. Using the historical data of monthly rent tags to establish a LightGBM (Light Gradient Boosting) model based on machine learning, the accurate forecast of housing monthly rent based on basic housing information is provided, which provides an objective measure for the city's rental market.

Keywords: Machine learning; Integrated learning; LightGBM (Light Gradient Boosting); Data mining; Rent forecasting