Predicting Boston Housing Price Using Machine Learning Models

DOI

10.2991/978-94-6463-542-3_51How to use a DOI?

Keywords

Multiple Regression Model; Random Forest; eXtreme Gradient Boosting

Abstract

In response to the ongoing rise in living expenses, especially the rise of rental prices, in Boston, people are increasingly inclined to explore alternative options for long-term financial savings. Compared to having an expense with no ownership, purchasing real estate is one of the top optimal options as it serves as a long-term investment. Given this big environment, utilizing predictive machine learning models (MLM) is a way for people to figure out the factors that influence Boston housing prices. Although most of the existing research utilized advanced MLM techniques or a combination of several regression models to increase the accuracy of the prediction, a few studies focus on basic MLM. In this paper, three traditional models are utilized to predict the features that affect Boston housing prices: the Multiple Regression Model (MLR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). The paper uses the Interquartile Range (IQR) method to remove the outliers in the dataset and handles the missing values by checking the amount and dropping them. Last but not least, the research uses R-squared, adjusted R-squared, cross-validated R-squared, and Root Mean Square Error (RMSE) as performance indicators of those models. The result shows that XGBoost has the best performance among the others.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hanqiu Ding
PY  - 2024
DA  - 2024/10/15
TI  - Predicting Boston Housing Price Using Machine Learning Models
BT  - Proceedings of the 2024 2nd International Conference on Management Innovation and Economy Development (MIED 2024)
PB  - Atlantis Press
SP  - 439
EP  - 444
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-542-3_51
DO  - 10.2991/978-94-6463-542-3_51
ID  - Ding2024
ER  -