NORMA eResearch @NCI Library

Novel Genetic Algorithms for Optimization of House Price Prediction: USA

Patterson, Ian (2021) Novel Genetic Algorithms for Optimization of House Price Prediction: USA. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Genetic Algorithms and their variants are popular methods of feature selection optimisation, with applications ranging from medical image denoising to structural engineering and stock market prediction. Innovations in the Genetic Algorithm itself have been limited, and not biologically-inspired. In this investigation, standard and novel biologically-inspired Genetic Algorithms are used to optimize the feature selection component of a machine learning-based House Price Prediction application. This analysis found the novel Co-Location and Multi-Chromosomal Genetic Algorithms to achieve superior optimization of XGBoost, Linear Regression and Decision Tree-mediated prediction. The Co-location Genetic Algorithm reduced Decision Tree prediction error by an additional 20%, as compared to the Standard Genetic Algorithm. The Multi-Chromosomal Genetic Algorithm reduced the required number of features for XGBoost and Decision Tree to achieve optimal prediction error, by 31% and 32% respectively, as compared to the Standard Genetic Algorithm. These optimal performances were also achieved with fewer generations of evolution required, corresponding to reduced computational cost. This finding has implications for all house price prediction analyses in which feature selection is mediated by genetic algorithms. Further investigation of the utility of these novel genetic algorithms across different domains may have implications for all applications of genetic algorithms, regardless of industry or application.

Item Type: Thesis (Masters)
Subjects: E History America > E151 United States (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 > Specific Industries > Property Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 14 Dec 2021 10:29
Last Modified: 14 Dec 2021 10:29

Actions (login required)

View Item View Item