Abstract
Aiming at the shortcomings of a single machine learning model with low model prediction accuracy and insufficient generalization ability in house price index prediction, a whale algorithm optimized support vector regression model based on bagging ensemble learning method is proposed. Firstly, gray correlation analysis is used to obtain the main influencing factors of house prices, and the segmentation forecasting method is used to divide the data set and forecast the house prices in the coming year using the data of the past ten years. Secondly, the whale optimization algorithm is used to find the optimal parameters of the penalty factor and kernel function in the SVR model, and then, the WOA-SVR model is established. Finally, in order to further improve the model generalization capability, a bagging integration strategy is used to further integrate and optimize the WOA-SVR model. The experiments are conducted to forecast the house price indices of four regions, Beijing, Shanghai, Tianjin, and Chongqing, respectively, and the results show that the prediction accuracy of the proposed integrated model is better than the comparison model in all cases.
Highlights
As a pillar industry of the national economy, real estate plays an indispensable role in promoting China’s economic development
From the results in the table, it can be seen that, in the prediction index results of all years, the prediction results of the models after bagging integration are better than their corresponding single models, while the bagging-whale optimization algorithm (WOA)-support vector regression (SVR) model has the best prediction effect among the four data sets, which fully proves that the bagging integration strategy can effectively improve the model prediction accuracy
In the prediction results of the Beijing dataset, the mean square error (MSE) results of the baggingBPNN model in the third and fifth years performed well, in the first and second years’ predictions, the bagging-WOASVR improved by 74.25% and 84.31%, respectively, relative to the bagging-BPNN, which significantly outperformed the bagging-BPNN. erefore, the bagging-WOA-SVR model has better stability and can achieve high accuracy forecasting of house price index data
Summary
As a pillar industry of the national economy, real estate plays an indispensable role in promoting China’s economic development. SVR is a regression prediction model based on the principle of structural risk minimization, which performs well under small sample and high-dimensional data sample conditions with better generalization and nonlinear fitting ability compared to BP neural network models [7]. A single machine learning model has poor generalization ability when making predictions, which makes it difficult to achieve high-precision predictions for house price data. Yang et al [15] proposed a bagging integrated extreme learning machine (ELM) to predict the path of tropical cyclones in the South China Sea and demonstrated experimentally that the integrated model has high generalization ability. The bagging ensemble learning strategy is used to integrate the WOA-SVR model for prediction in order to further improve the generalization ability and prediction accuracy of the model.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
