NORMA eResearch @NCI Library

House Price Prediction using Genetic algorithms and Tree-based methods for feature selection: The case of House Pricing in King County, USA

Mhaske, Nihar Devidas (2022) House Price Prediction using Genetic algorithms and Tree-based methods for feature selection: The case of House Pricing in King County, USA. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

The housing market is unstable and complex considering that it is impacted by the economic situation and a wide range of other factors. The housing market has the potential to contribute to economic stability. It is important to understand the housing market in to develop measures to promote sustainable and healthy housing values. The study aims to compare the performance of machine learning with two different feature selection techniques in predicting property sale prices. In this study, two machine models, Extreme gradient boosting and Random Forest, were implemented using a tree-based technique and genetic algorithms for feature selection. The model performed on the features selected by the tree-based approach has performed better than the genetic algorithm. In this study, the R2 score, mean absolute error, and cross-validation evaluation metrics were used to classify the model. Hyperparameter tuning was used to improve model performance. The implementation of models showed that the Random Forest model, which used a tree-based approach for feature selection, had the best performance in terms R2 score , MAE and RMSE compared to genetic feature selection models.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HD Industries. Land use. Labor > Housing
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Property Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 23 Feb 2023 12:42
Last Modified: 02 Mar 2023 08:55
URI: https://norma.ncirl.ie/id/eprint/6228

Actions (login required)

View Item View Item