A Computational Intelligence-Based Prediction Model for Flight Departure Delays

Abstract

Flight departure delays are a major problem at OR Tambo International airport (ORTIA) located in Johannesburg in South Africa. These delays are more pronounced at the beginning and end of the month. Flight delays at ORTIA do impact negatively on business, on job opportunities and on tourists. Machine learning algorithms namely Decision Trees (J48), Support Vector Machine (SVM), K-Means Clustering (K-Means) and Multi Layered Perceptron (MLP) were used to construct the flight departure delays prediction models. Cross-validation (CV) was used for evaluating the models. The best prediction model was selected by using a confusion matrix and the ROC curve. The results show that the models constructed using data and the Decision Trees is suited for flight departure delay prediction as it gave the best prediction of 67.144%. The implications of the model is that travellers wishing to travel from ORTIA can foretell the flight departure delays using the tool. The tool will allow the travellers to enter variables such as month, week of month, day of week and time of day.