Research Article
Research on the Prediction Model of House Rent Based on Machine Learning
@INPROCEEDINGS{10.4108/eai.19-5-2023.2334250, author={Hongtao Zong and Jihong Song}, title={Research on the Prediction Model of House Rent Based on Machine Learning}, proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2023}, month={7}, keywords={machine learning; svr model; gbrt model; knn algorithm; rent prediction}, doi={10.4108/eai.19-5-2023.2334250} }- Hongtao Zong
Jihong Song
Year: 2023
Research on the Prediction Model of House Rent Based on Machine Learning
ICBBEM
EAI
DOI: 10.4108/eai.19-5-2023.2334250
Abstract
How to provide renters with rent reference based on housing characteristics is an urgent issue to be solved, and GBRT (Gradient Boosting Regression Tree) provides a solution to the rent prediction problem. However, in GBRT, there is a problem that the accuracy of model prediction is not ideal due to the fact that the average value is used as the output value for the subset of node samples when constructing a tree, and all training samples arriving at a certain leaf node are equally considered, which relies too heavily on data quality. This paper uses KNN algorithm to perform weighted averaging based on the contribution of neighboring points to the prediction results, and combines the advantages of SVR in processing high-dimensional data and small samples, and proposes SVR and KNN_GBRT fusion model. The improved fusion model has been validated in a housing rental datasets and has better prediction results compared to SVR model and GBRT model.