Prediction of fuel usage consumption in the airline industry
No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Author
Date
2024-03-11
Department
Major/Subject
Data Science
Mcode
SCI3115
Degree programme
Master's Programme in ICT Innovation
Language
en
Pages
38
Series
Abstract
This document presents a study on the prediction of fuel usage consumption in the airline industry using machine learning methods. The research aims to apply and compare different machine learning models to real-world data on various factors that influence fuel consumption during flights. The models evaluated include linear regression, polynomial regression, neural network, decision tree, random forest, support vector machine, gradient boosting regression, and AdaBoost regression. The results show that some of the machine learning models, such as Random Forest and Gradient Boosting Regression, performed well on the prediction task, while others, such as Adaptive Boosting Regression, showed limitations and weaknesses. The study has implications for the airline industry, especially in terms of cost forecasting, efficiency optimization, and sustainability enhancement. The research is concluded by suggesting some possible directions for future research, such as incorporating more features, testing new models, and applying the models to different scenarios.Description
Supervisor
Jung, AlexanderThesis advisor
Juhasz, BertalanKeywords
fuel, consumption, prediction, usage, forecasting
