Abstract
In the paper, the flight time deviation of Lithuania airports has been analyzed. The supervised machine learning model has been implemented to predict the interval of time delay deviation of new flights. The analysis has been made using seven algorithms: probabilistic neural network, multilayer perceptron, decision trees, random forest, tree ensemble, gradient boosted trees, and support vector machines. To find the best parameters which give the highest accuracy for each algorithm, the grid search has been used. To evaluate the quality of each algorithm, the five measures have been calculated: sensitivity/recall, precision, specificity, F-measure, and accuracy. All experimental investigation has been made using the newly collected dataset from Lithuania airports and weather information on departure/landing time. The departure flights and arrival flights have been investigated separately. To balance the dataset, the SMOTE technique is used. The research results showed that the highest accuracy is obtained using the tree model classifiers and the best algorithm of this type to predict is gradient boosted trees.
Highlights
For all airlines, flight time deviation from scheduled times brings financial, coordination, or technical difficulties
In the research [3], the spatial analysis has been used to find the factors which influence the departure flight delay. e research results show that, in many cases, weather is one of the most important factors, so the weather-induced prediction methods are proposed in [4], a lot depends on the size and activity of the analyzed airport. e small airport has not many flights in 24 h; the arrival time delay depends mostly on the reactionary type, and in the case of departure flight, deviation time is usually small
A deeper literature analysis showed that the gradient boosted trees are one of the common classification algorithm used for flight delays when dataset size is big [19, 20]. e model accuracy using this algorithm is mostly always higher compared to other algorithms. e problem is that, in all cases, the results depend on various factors: dataset size, attributed number, attribute types, parameters used for each model, testing, etc
Summary
Flight time deviation from scheduled times brings financial, coordination, or technical difficulties. E small airport has not many flights in 24 h; the arrival time delay depends mostly on the reactionary type, and in the case of departure flight, deviation time is usually small. E main aim of this paper is to find the best classification algorithm used in machine learning which can be suitable to adapt results for small airports delay analysis. E newly collected dataset of Lithuania airport flight information and local area weather information are analyzed to predict possible flight time deviation from scheduled time [8]. In the paper, suggested data collecting model can be adapted for various countries airports analysis At this moment, the dataset is not big but constantly updated; so in the future, the obtained results should be more accurate.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
