Forecasting fuel surcharge application for air freight price determination | |
| Author | Pumpath Sukhsomchiswichai |
| Call Number | AIT RSPR no.IM-24-04 |
| Subject(s) | Aeronautics, Commercial--Fuel--Prices--Forecasting Deep learning (Machine learning) Time-series analysis |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | Global air cargo demand has increased dramatically from the past to present, in accor dance with excessive demand from electronic platforms causing e-commerce though B2Bor B2Cbusinesses to push air cargo demand up to the threshold. Fuel surcharge is one of the price elements in air cargo business, hence this study has examined the his torical data of fuel surcharge implementation in Thailand from 2015-2023 announced by airline operators in Thailand.The main objective of this study is to investigate fuel charge characteristics and development patterns for prediction. Additionally, the study also implements a time se ries forecasting model to predict future fuel surcharge level, evaluates the best suitable model for specific data characteristics aimed for prediction accuracy of air freight price establishment on air freight logistics domain.The study found many strong relationships from correlation analysis between various factors such as crude oil price and exchange rates as well as fuel surcharge level. The study found the ARIMA model provides best accuracy in prediction results compared to SVMand other Deep Learning models. Finally ARIMA is selected for this study to perform the prediction advancement to obtain future fuel surcharge level. From the forecasting, the study found ARIMA of fers the most accurate prediction for short term prediction rather than long term result. However it is more understandable when shorter prediction is more accurate than longer term prediction. In conclusion, prediction of historic data also enhances future prediction performance with appropriate models selected for existing data and prediction direction. |
| Year | 2024 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Vatcharapon Esichaikul; |
| Examination Committee(s) | Chutiporn Anutariya;Huynh, Trung Luong; |
| Scholarship Donor(s) | AIT Scholarship; |
| Degree | Research studies project report (M. Sc.) - Asian Institute of Technology, 2024 |