Predicting Housing Prices Using Structural Attributes and Distance to Nearby Schools

Abou Hassan, Mohammed (2018) Predicting Housing Prices Using Structural Attributes and Distance to Nearby Schools. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

Objective: Housing is a basic human need and buying one is an important decision that should be made carefully as it leads to future financial commitment. Developing a model that can help buyers make this decision by predicting the price of a house is of extreme importance. This work will investigate to what extent the performance of the predicting model can be improved by taking the distance to nearby schools into account.

Background: Early studies used different types of regression models, each trying to approach the research question in a different way with one thing in common; these models produced good predictions only when the researcher was able to make solid statistical assumptions which required a lot of domain knowledge and experience in statistical modelling.

Methods: To overcome these challenges, this work will use a machine learning approach. It requires no domain knowledge and was proved to produce excellent results even if the data had non-linear relationships. The dataset to be used in this work will include structural attributes like number of bedrooms and bathrooms and one locational attribute which is the distance to the nearest school. Artificial Neural Networks (ANN) was proved reliable for housing price predictions in earlier research and this work will aim at investigating how the accuracy of such models will change when distance to the nearest school is added to the model.

Results: Two ANN models were built, one that includes the distance to school feature and another model that does not. The results of R squared of the two models were compared to find the one that performed better. The results showed that the model that includes the distance to the nearest school scored 1% less.

Item Type:	Thesis (Masters)
Subjects:	L Education > L Education (General) Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software H Social Sciences > HD Industries. Land use. Labor > Housing
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	05 Nov 2018 10:22
Last Modified:	05 Nov 2018 10:30
URI:	https://norma.ncirl.ie/id/eprint/3423

Actions (login required)

View Item