Real estate price prediction research method based on gradient boosting decision tree hybrid model

Abstract

The invention discloses a real estate price prediction research method based on a gradient boosting decision tree hybrid model. The method comprises the following steps: 1) obtaining network search data and real estate price data; 2) screening out an advanced keyword having high correlation with the real estate price from the network search data and the real estate price data by calculating a Spearman correlation coefficient and carrying out time difference correlation analysis; 3) establishing a long-term and short-term memory model, and predicting the real estate price through the long-termand short-term memory model; 4) establishing a support vector regression model, and predicting the real estate price by using the support vector regression model; and 5) taking the predicted value ofthe real estate price obtained in the step 3) and the predicted value of the real estate price obtained in the step 4) as an original sample set of the gradient boosting decision tree hybrid model, and performing prediction fusion by utilizing the gradient boosting decision tree hybrid model. The real estate price prediction method can accurately predict the real estate price.

Description

technical field [0001] The invention belongs to the field of real estate, and relates to a real estate price prediction research method based on a gradient lifting decision tree mixed model. Background technique [0002] The rapid development of the Internet has promoted the arrival of the era of big data, which has a huge impact on people's activities and decision-making from many aspects. A large number of consumers are accustomed to using search engines to retrieve effective information before making decisions. As of December 2018, the number of netizens in my country reached 829 million, with an Internet penetration rate of 59.2%, and the number of netizens is still increasing year by year. In recent years, the Internet has been gradually applied to many social and economic fields, including the real estate industry. As the pillar industry of our country's national economy, the real estate industry has always been in a vital position in the development of our national e...

AI Technical Summary

Problems solved by technology

[0004] The above are the achievements of machine learning methods in the field of real estate price prediction research, but these models still have a certain loss function, which affects the prediction results, and only consider the correlation between variables when screening data, ignoring the time series Time lag of data, poor prediction accuracy

Images