Predictive Modeling of Flight Delays at an Airport Using Machine Learning Methods
Source abstract
Abstract
Flight delays represent a significant challenge in the global aviation industry, resulting in substantial costs and a decline in passenger satisfaction. This study addresses the critical issue of predicting flight delays exceeding 15 min using machine learning techniques. The arrival delays at a Turkish airport are analyzed utilizing a novel dataset derived from airport operations. This research examines a range of machine learning models, including Logistic Regression, Naïve Bayes, Neural Networks, Random Forest, XGBoost, CatBoost, and LightGBM. To address the issue of imbalanced data, additional experiments are conducted using the Synthetic Minority Over-Sampling Technique (SMOTE), in conjunction with the incorporation of meteorological data. This multi-faceted approach ensures robust forecast performance under varying conditions. The SHAP (SHapley Additive exPlanations) method is employed to interpret the relative importance of features within the models. The study is based on a three-year period of flight data obtained from a Turkish airport. The dataset is sufficiently extensive and robust to provide a reliable foundation for analysis. The results indicate that XGBoost is the most proficient model for the dataset, demonstrating its potential to deliver highly accurate predictions with an accuracy of 80%. The impact of weather factors on the predictions is found to be insignificant in comparison to scenarios without weather data in this dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Traffic Management and Optimization · Aviation Industry Analysis and Trends · Aerospace and Aviation Technology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of International Trade and Logistics, Faculty of Applied Sciences, Akdeniz University, Antalya 07070, Turkey
Department of Management Information Systems, Faculty of Applied Sciences, Akdeniz University, Antalya 07070, Turkey
References (68)
Show source-provided references
1. Schrader, R. (2023). How Far in Advance Can You Book a Flight?, Skyscanner. Available online: https://www.skyscanner.com/tips-and-inspiration/how-far-in-advance-can-you-book-a-flight#:~:text=The bottom line-,How far in advance can you book a flight%3F,of factors can influence that.&text=You should keep in mind,points to book your ticket.
2. FAA (2022, April 01). Cost of Delay Estimates, Federal Aviation Administration, Available online: https://www.faa.gov/data_research/aviation_data_statistics/media/cost_delay_estimates.pdf.
3. Yang, C., Marshall, Z.A., and Mott, J.H. (2020, January 24). A Novel Integration Platform to Reduce Flight Delays in the National Airspace System. Proceedings of the 2020 Systems and Information Engineering Design Symposium, Charlottesville, VA, USA.10.1109/SIEDS49339.2020.9106657 ↗
4. Transportation Research Board (2002). Future Flight: A Review of the Small Aircraft Transportation System Concept, National Academy Press.
5. Analyzing passengers’ emotions following flight delays—A 2011–2019 case study on SKYTRAX comments10.1016/j.jairtraman.2020.101903 ↗
6. The behavioral consequences of repeated flight delays10.1016/j.jairtraman.2011.11.001 ↗
7. Shaw, S. (2007). Airline Marketing and Management, Ashgate. [6th ed.].
8. The impact of flight delays on passenger demand and societal welfare10.1016/j.tre.2011.10.009 ↗
9. The impact of delays on customers’ satisfaction: An empirical analysis of the british airways on-time performance at heathrow airport
10. Ball, M., Barnhart, C., Dresner, M., Hansen, M., Neels, K., Odoni, A., Peterson, E., Sherry, L., Trani, A., and Zou, B. (2010). Total Delay Impact Study, The National Center of Excellence for Aviation Operations Research.
11. Daley, B. (2010). Air Transport and the Environment, Routledge.
12. Federal Aviation Administration (2022, April 01). (n.d.), Delay, Available online: https://aspm.faa.gov/aspmhelp/index/Types_of_Delay.html.
13. Brownlee, J. (2020). SMOTE for Imbalanced Classification with Python, Machine Learning Mastery. Available online: https://machinelearningmastery.com/smote-oversampling-for-imbalanced-classification/.
14. A statistical study of the weather impact on punctuality at Frankfurt Airport10.1002/met.74 ↗
15. Multifactor model for predicting delays at U.S. airports10.3141/2052-08 ↗
16. Does competition increase quality? Evidence from the US airline industry10.1016/j.ijindorg.2021.102742 ↗
17. A survival model for flight delay propagation10.1016/j.jairtraman.2012.01.016 ↗
18. Optimizing Arrival Flight Delay Scheduling Based on Simulated Annealing Algorithm10.1016/j.phpro.2012.05.073 ↗
19. Planning for Robust Airline Operations: Optimizing Aircraft Routings and Flight Departure Times to Minimize Passenger Disruptions10.1287/trsc.1050.0134 ↗
20. Uncertainty-Aware Flight Scheduling for Airport Throughput and Flight Delay Optimization10.1109/TAES.2019.2921193 ↗
21. Forecasting Flight Delays Using Clustered Models Based on Airport Networks
22. Helme, M.P. (1992, January 18–21). Reducing air traffic delay in a space-time network. Proceedings of the 1992 IEEE International Conference on Systems, Man, and Cybernetics, Chicago, IL, USA.
23. Study on Delay Propagation Relations Among Airports Based on Transfer Entropy10.1109/ACCESS.2020.2996301 ↗
24. Network analysis of Chinese air transport delay propagation10.1016/j.cja.2017.01.012 ↗
25. Characterization and prediction of air traffic delays10.1016/j.trc.2014.04.007 ↗
26. Choi, S., Kim, Y.J., Briceno, S., and Mavris, D. (2016, January 25–29). Prediction of Weather-induced Airline Delays Based on Machine Learning Algorithms. Proceedings of the 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), Sacramento, CA, USA.10.1109/DASC.2016.7777956 ↗
27. Kim, Y.J., Choi, S., Briceno, S., and Mavris, D. (2016, January 25–29). A deep learning approach to flight delay prediction. Proceedings of the 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), Sacramento, CA, USA.10.1109/DASC.2016.7778092 ↗
28. Using scalable data mining for predicting flight delays10.1145/2888402 ↗
29. Manna, S., Biswas, S., Kundu, R., Rakshit, S., Gupta, P., and Barman, S. (2017, January 2–3). A statistical approach to predict flight delay using gradient boosted decision tree. Proceedings of the 2017 International Conference on Computational Intelligence in Data Science, Chennai, India.10.1109/ICCIDS.2017.8272656 ↗
30. Takeichi, N., Kaida, R., Shimomura, A., and Yamauchi, T. (2017, January 9–13). Prediction of delay due to air traffic control by machine learning. Proceedings of the AIAA Modeling and Simulation Technologies Conference, Grapevine, TX, USA.10.2514/6.2017-1323 ↗
31. Thiagarajan, B., Srinivasan, L., Sharma, A.V., Sreekanthan, D., and Vijayaraghavan, V. (2017, January 17–21). A machine learning approach for prediction of on-time performance of flights. Proceedings of the 2017 IEEE/AIAA 36th Digital Avionics Systems Conference (DASC), St. Petersburg, FL, USA.10.1109/DASC.2017.8102138 ↗
32. Venkatesh, V., Arya, A., Agarwal, P., Lakshmi, S., and Balana, S. (2017, January 26–28). Iterative machine and deep learning approach for aviation delay prediction. Proceedings of the 2017 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics (UPCON), Mathura, India.10.1109/UPCON.2017.8251111 ↗
33. Performance analysis of machine learning techniques on big data using apache spark
34. Machine Learning Techniques for Analysis of Egyptian Flight Delay
35. Nigam, R., and Govinda, K. (2017, January 7–8). Cloud based flight delay prediction using logistic regression. Proceedings of the 2017 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India.10.1109/ISS1.2017.8389254 ↗
36. Moreira, L., Dantas, C., Oliveira, L., Soares, J., and Ogasawara, E. (2018, January 8–13). On Evaluating Data Preprocessing Methods for Machine Learning Models for Flight Delays. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489294 ↗
37. Flight delay prediction for commercial air transport: A deep learning approach10.1016/j.tre.2019.03.013 ↗
38. Chen, J., and Li, M. (2019, January 7–11). Chained predictions of flight delay using machine learning. Proceedings of the AIAA Scitech 2019 Forum, San Diego, CA, USA.10.2514/6.2019-1661 ↗
39. Mangortey, E., Pinon, O.J., Puranik, T.G., and Mavris, D.N. (2019, January 17–21). Predicting the occurrence of weather and volume related ground delay programs. Proceedings of the AIAA Aviation 2019 Forum, Dallas, TX, USA.10.2514/6.2019-3188 ↗
40. McCarthy, N., Karzand, M., Lecue, F., Kim, Y.J., Choi, S., Briceno, S., Mavris, D., Yazdi, M.F., Kamel, S.R., and Chabok, S.J.M. (February, January 27). Amsterdam to Dublin eventually delayed? Lstm and transfer learning for predicting delays of low cost airlines. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
41. Airline delay prediction by machine learning algorithms
42. Meel, P., Singhal, M., Tanwar, M., and Saini, N. (2020, January 27–28). Predicting Flight Delays with Error Calculation using Machine Learned Classifiers. Proceedings of the 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India.10.1109/SPIN48934.2020.9071159 ↗
43. Dou, X. (2020, January 12–14). Flight Arrival Delay Prediction and Analysis Using Ensemble Learning. Proceedings of the 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chongqing, China.10.1109/ITNEC48623.2020.9084929 ↗
44. Empirical Study on Airline Delay Analysis and Prediction
45. Flight delay prediction based on aviation big data and machine learning10.1109/TVT.2019.2954094 ↗
46. Flight delay prediction based on deep learning and Levenberg-Marquart algorithm10.1186/s40537-020-00380-z ↗
47. Machine Learning Approach for Flight Departure Delay Prediction and Analysis10.1177/0361198120930014 ↗
48. A system for effectively predicting flight delays based on IoT data10.1007/s00607-020-00794-w ↗
49. Liu, F., Sun, J., Liu, M., Yang, J., and Gui, G. (2020, January 25–28). Generalized Flight Delay Prediction Method Using Gradient Boosting Decision Tree. Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium.10.1109/VTC2020-Spring48590.2020.9129110 ↗
50. Zheng, A. (2015). Evaluating Machine Learning Models A Beginner’s Guide to Key Concepts and Pitfalls, O’Reilly.
51. Detection of Diabetes and Cholesterol
52. Dimitoglou, G., Adams, J.A., and Jim, C.M. (2012). Comparison of the C4.5 and a Naive Bayes Classifier for the Prediction of Lung Cancer Survivability. arXiv.
53. Graupe, D. (2013). Principles Of Artificial Neural Networks, World Scientific. [3rd ed.].10.1142/8868 ↗
54. Mijwil, M.M. (2018). Artificial Neural Networks Advantages and Disadvantages, Bagdad College of Economic Science University. Available online: https://www.researchgate.net/publication/323665827.
55. The Regression Analysis of Binary Sequences10.1111/j.2517-6161.1958.tb00292.x ↗
56. Bankruptcy prediction: Application of the Taylor’s expansion in logistic regression10.1016/S1057-5219(00)00039-9 ↗
57. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes10.1016/S0895-4356(96)00002-9 ↗
58. Random Forests10.1023/A:1010950718922 ↗
59. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
60. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017, January 4–9). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
61. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018, January 3–8). Catboost: Unbiased boosting with categorical features. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
62. Factors influencing charter flight departure delay
63. Assessing strategic flight schedules at an airport using machine learning-based flight delay and cancellation predictions10.1016/j.jairtraman.2019.101737 ↗
64. A Preliminary Study on Learning Challenges in Machine Learning-based Flight Delay Prediction10.11113/ijic.v9n1.204 ↗
65. The impact of airline flight schedules on flight delays10.1287/msom.1120.0379 ↗
66. A structural vector autoregressive model of technical efficiency and delays with an application to Chinese airlines10.1016/j.tra.2017.05.003 ↗
67. Fernández, A., García, S., Galar, M., and Prati, R.C. (2019). Learning from Imbalanced Data Sets, Springer.10.1007/978-3-319-98074-4 ↗
68. Lundberg, S.M., and Lee, S.I. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.