Ensemble Stacking and Optimisation For Annual Revenue Prediction of Individual Airbnb Hosting: Italy

Min, Junghyun (2023) Ensemble Stacking and Optimisation For Annual Revenue Prediction of Individual Airbnb Hosting: Italy. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This project aimed to build ensemble stacking machine learning models with hyperparameter optimisation(HPO) for a profitability prediction in 10 different cities of Italian Airbnb data. The main goal was that successfully performed modelling, prediction and evaluation by comparing HPO methods on ensemble stacking models. Another research point was to identify factors that influenced target data, Airbnb profitability, and explore differences across 10 Italian cities. Various regression machine learning techniques, including random forest, Gradient Boosting, LightGBM, XGBoost and ensemble stacking, were employed to achieve this. The ensemble stacking model was built by the use of XGBoost as a meta-model and the other models as base learners. After model buildings, hyperparameter tuning methods were applied using a combination of random search and Bayesian optimization methods carefully selected for this study. The findings of this research could provide optimum ensemble and hyperparameter tuning methods for B&B data and contribute valuable insights into the key factors of Airbnb’s profitability for strategic decision-making.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Uncontrolled Keywords:	Airbnb; Ensemble Machine Learning; Ensemble Stacking; Bayesian Optimisation; Genetic Algorithm
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Hospitality Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	29 Nov 2024 13:29
Last Modified:	29 Nov 2024 13:29
URI:	https://norma.ncirl.ie/id/eprint/7213

Actions (login required)

View Item