This study focuses on developing a robust flight delay prediction model by analyzing historical flight data, incorporating factors such as departure and arrival times, weather conditions, aircraft type, and airline details. Machine learning approaches, specifically the Artificial Neural Network (ANN) Algorithm and Auto Regressive Integrated Moving Average (ARIMA), were employed to predict estimated flight delays. Two groups were sampled during the pretest power analysis with an 80% confidence level. The ANN algorithm showed an accuracy level of 86.90%, surpassing the ARIMA algorithm with an accuracy level of 85.94%. By conducting independent sample T-tests with a significance level of 0.05, the ANN algorithm was proven to be superior, with a statistically significant difference in accuracy. These results underscore the potential of the ANN model in enhancing the precision of flight delay predictions, contributing to the optimization of air travel planning and operations, and ultimately improving the overall efficiency of the aviation industry.
Flight Delay Prediction for Air Travel Management Using Artificial Neural Network Compared with Auto Regressive Integrated Moving Average Algorithm
2024-04-18
249019 byte
Conference paper
Electronic Resource
English
Aviation Accident Prediction Based on Auto-Regressive Integrating Moving Average Method
Trans Tech Publications | 2013
|Short-term traffic-flow forecasting with auto-regressive moving average models
Online Contents | 2014
|British Library Conference Proceedings | 2007
|Bus travel time prediction: a log-normal auto-regressive (AR) modelling approach
Taylor & Francis Verlag | 2020
|Auto-regressive Image Synthesis with Integrated Quantization
British Library Conference Proceedings | 2022
|