PREDICTION OF FUTURE FLIGHT DELAYS BASED ON CURRENT DATA ANALYSIS USING MACHINE LEARNING

The usage of big data analytics is booming today, with its ability to be used to draw useful insights from past data research. Its uses in the aviation industry have a wide array of applications ranging from predicting flight delays to detecting faults in airplane parts. In this paper, we conducted exploratory data analysis on flight dataset to draw inferences on arrival and departure delays and to identify relationships between flight timings and delays. Using the flight delay data, we identified which flight is mostly prone to delays. The arrived upon conclusions are useful for selecting flights in the future.

Due to the large span of flight delay, numerous influencing factors and large number of flights, the collected flight delay data is characterized by large-scale and imbalance, which is considered as one of the largest challenges in balanced flight delay data classification by using conventional classification algorithms. To solve this problem, an adaptive multi-class classification approach of imbalanced flight delay data using synthetic minority over-sampling technique (SMOTE)-based convolutional neural network with sparrow search algorithm, namely SSA-LTCNN is proposed in this paper. Firstly, the SMOTE is used to reduce the imbalance between the classes of the flight delay data. Then, the qualitative analysis method is employed to determine the key parameters of the CNN, which are optimized by using SSA to establish an optimized CNN model. Finally, the optimized CNN model with more effective feature representation ability is employed to extract discriminative features from the balanced flight delay data automatically. The obtained features in the last fully connected layer of the optimized CNN model are used for flight delay classification. The MIT-BIH Arrhythmia Data is selected to verify the effectiveness of the proposed SSA-LTCNN method and the confusion matrix, classification accuracy, precision, recall and F1 score are also used to evaluate the performance of the proposed SSA-LTCNN method, which can get better performance than RF, DT, LR, CNN and QRSCNN. The actual flight delay data is processed to verify the effectiveness of the proposed classification approach, which can achieve higher accuracy than KNN, NB, UCNN, CNN, SSA-LCNN and SSA-TCNN in different time periods. The experimental results show that the SSA-LTCNN can fast and effectively realize the classification of MIT-BIH Arrhythmia Data and flight delay data.

In recent years, flight delay costs the air transportation industry millions of dollars and has become a systematic problem. Understanding the behavior of flight delay is thus critical. This paper focuses on how flight delay is affected by operation-, time-, and weather-related factors. Different econometric models are developed to analyze departure and arrival delay. The results show that compared to departure delay, arrival delay is more likely to be affected by previous delays and the buffer effect. Block buffer presents a reduction effect seven times greater than turnaround buffer in terms of flight delays. Departure flights suffer more delays from convective weather than arrival flights. Convective weather at the destination airport for flight delay has a greater impact than at the original airport. In addition, sensitivity analysis of flight delays from an aircraft utilization perspective is conducted. We find that the effect of delay propagation on flight delay differs by aircraft utilization. This impact on departure delay is greater than the impact on arrival delay. In general, specific to the order of flights, the previous delay increases the impact on flight on-time performance as a flight flies a later leg. Buffer time has opposite effects on departure and arrival delay, with the order increasing. A decrease in buffer time with the order increasing, however, still has a greater reduction effect on departure delay than arrival delay. Specific to the number of flights operated by an aircraft, the more flights an aircraft flies in a day, the more the on-time performance of those flights will suffer from the previous delay and buffer time generally.

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.

With the development of the civil aviation transportation industry in recent years, the volume of civil aviation transportation has increased rapidly. Increased carrier costs and reduced airport operating efficiency caused by flight delays have become issues that need to be addressed. How to improve the accuracy of predicting flight arrival delay time is of great significance for improving airport transportation efficiency, rationally scheduling flights and improving passenger comfort. In this paper, the Cat-boost model is utilized on the U.S Domestic airline on-time performance data from U.S. Transportation Administration, combined with the characteristics of the model to determine the influencing factors, and to predict the arrival delays of flights within the United States. The accuracy;precision and some other criterion of the model are given to evaluate the performance on the data. A better effect is obtained: the accuracy reach 80.44% in this case. Finally, the specific delay time is predicted, we found that the support vector machine has the best prediction result for the flight delay time, the average prediction error is 9.733 min, which has a certain reference value for flight operation and airport scheduling.

Data-Driven Robust Aircraft Assignment to Minimize Delay Propagation

Efficiency measurement of Chinese airports with flight delays by directional distance function

Flight delay is the root of Delay Propagation, while delay propagated within a Flight Chain. Busy hub-airport plays an important role in a Flight Chain, since the Initial Delay often happens there. To research more possible impacting factors in the Flight Chain, a busy hub-airport is chosen as the object in this research. After analyzing the complex and uncertain relationship between flight delays and all possible impacting factors, Bayesian network (BN) adapt to model and estimate about flight delay in a busy hub-airport. We proposed two learning methods with three different models. Model I is an estimation model for Arrival Delay based on parameter learning of BN with the Expectation-Maximization (EM) algorithm. Model II is estimation model for Arrival Delay based on structure learning of BN with K2 algorithm. The model learned by K2 is proved more suitable for modeling the estimation of flight delay, with a higher estimating correct rate than Model I. Then Model II is estimation model for Departure Delay with the same algorithm of Model II.

PurposeThis study aims to investigate the effects of flight delays, distance, number of passengers and seasonality on revenue in the Turkish air transport industry.Design/methodology/approachThe domestic return routes of a Turkish airline company were examined to address this issue. Among five cities and six airports, 14 major domestic return routes were selected. The augmented mean group (AMG) estimator and common correlated effects mean group (CCEMG) estimator were conducted with a two-way fixed effects (FE) robustness test in this study.FindingsThe results show that arrival flight delay and departure flight delay had negative effects on revenue, whereas the distance between airports, the number of air passengers and seasonality had positive effects on revenue.Research limitations/implicationsThe data used in this study were retrieved from a Turkish airline company; for future research, other airline companies operating in Turkey may be included.Practical implicationsThese findings could be evaluated by air transportation leaders to provide a guide to make strategic decisions to achieve greater performance in this competitive environment.Originality/valueThe originality of the paper comes from the facts that besides distance and number of passengers, the authors control for the seasonality when assessing the effects of flight delay on revenue; they use panel data techniques, which permit them to control for individual heterogeneity, and create more variability, more efficiency and less collinearity among the variables; they use two recent panel data techniques, CCEMG and AMG, allowing for cross-section dependence.

The purpose of this paper is to combine the cloud model method with the Artificial neural network to predict and evaluate flight delay date. In this paper, the flight delay data of the United States in recent 15 years were collected, involving nine airlines and seven delay causes. Then, the flight delay prediction model is obtained by combining neural network and cloud model theory. 36 sets of data are extracted to verify the accuracy of the prediction model. Finally, the delay rate is predicted and the prediction data is evaluated by cloud model. The results show that the amount of data to be processed is reduced to 20 % after combining the cloud model with the neural network. In the model validation, the average expected value deviation of flight delay prediction model is 23.1 %. In the analysis and evaluation of the prediction results, the delay cause 6 is taken as an example, with the highest delay rate of 7.03 % in December. The delay risk assessment results for all months were general. The method provided in this paper can predict flight delays and provide theoretical support for the delay prevention of airlines.

Delays in arrival of airline passengers should be the on-time performance metric of the airline passenger transportation system (not flight delays). A passenger trip can experience arrival delays, relative to the ticketed arrival time, as a result of a delayed flight, as well as a diverted flight, cancelled flight, denied boarding, and/or missed connection. This paper describes the results of analysis of annual passenger trip delays for U.S. domestic airline flights from 2007 to 2009. These results are based on estimated itineraries and load factors, and actual airline (flight) on-time performance data available from government websites.

This research consists of an introduction and four independent papers (though related) on the growth determinants of Ethiopian air transport in general and efficiency analysis of Ethiopian airports’ in particular. This introduction also highlights the concept of the research and provides an overview of the aviation sector’s performance including the rationale for the study and the contribution that the four papers make to existing literature on air transport. These four distinct studies use different model specifications, estimations and ranking of the performance of the airlines and airports. The differences in the airports’ performance are attributed to the objectives of the airports, data availability, the structure and the model’s underlying assumptions. To begin with, the first paper uses a cost minimization or input oriented approach for analyzing the cost efficiency of Ethiopian airports using the panel data stochastic frontier approach. It uses the time-invariant fixed effects, time-variant true fixed effects, specifying and estimating the time variant and time invariant approaches in (Kumbhakar et al., A practitioner's guide to stochastic frontier analysis using Stata (No, Cambridge University Press, BOOK), 2015) and (Battese and Coelli, Empirical Economics 20:325–332, 1995) models. The empirical findings elaborated international airports having higher passenger volumes attributing to lower cost efficiency compared to domestic airports. In other words, maximum cost efficiency was found at airports with low levels of services and facilities as compared to airports with better services and advanced facilities. The findings also show that airports having better infrastructure and airport specific facilities and services will continue to be inefficient compared to those having lower levels of facilities and services. Ethiopian airports should therefore introduce cost saving approaches based on reliable traffic forecasts. The second paper uses an output maximization or output oriented approach for analyzing the production efficiency of domestic and international Ethiopian airports using the stochastic frontier panel data approach for the period 2002–17. This study examines the technical efficiency of Ethiopian airports over time. It specifies (Kumbhakar et al., J Prod Anal 41:321–337, 2014) maximum likelihood method for separating persistent time-invariant inefficiency and transitory time-varying inefficiency from an unobservable individual effects. It also applies the fixed effects model and distance technical inefficiency using (Battese and Coelli, Empirical Economics 20:325–332, 1995) approach for a comparison. The findings indicate that most Ethiopian airports have relatively low technical efficiency which is required for developing competitive strategies that can attract more air traffic volumes and generate higher revenues. Classic customer handling, policy, and incentive schemes should therefore be introduced to increase passenger demand. Private and low-cost carriers should be encouraged to operate using the airports’ services. The third paper uses a factor demand approach and focuses on Ethiopian airports’ labor use efficiency by analyzing the panel data stochastic frontier input requirement function. It also specifies the (Kumbhakar and Heshmati, Am J Agr Econ 77:660–674, 1995) model and maximum likelihood estimation techniques of separating persistent time-invariant inefficiency and transitory time-varying inefficiency for estimating labor use efficiency of Ethiopian airports. The findings show that domestic airports are relatively better performing as compared to international airports. Similarly, most airports experience high persistent inefficiencies compared to transitory inefficiencies. This implies a need for taking lessons in the deployment of labor resources and introducing minimum labor requirement standards at all airports. The final paper examines the growth determinants of the Ethiopian air transport sector by testing the variables’ significance and the causality of the three separate but interdependent activity equations covering the period 1988–2018. Ethiopian Airlines’ passenger growth determinants, other airlines’ passenger growth determinants, and the determinants of air freight cargo growth. In this research, ordinary least squares, a seemingly unrelated regression estimation, and autoregressive distributed lag modelling approaches are applied to investigate the short-run and long-run causal relationships between air transport growth and some selected macroeconomic variables. The major findings show that most variables are statistically significant both in the short-run and long-run. Similarly, their respective error correction models are also significant and negative as expected implying strong and significant causal relationships between the short-run and long-run models. The econometric results of some specific variables vary which is attributed to high dependency on imported goods and services, absence of alternative passenger air transport systems, and steadily growing aggregate demand for air transport. The government should therefore pay due attention to stable macroeconomic growth and airlines also should have long-run strategic planning for reducing the effects of any internal and external shocks to the economy.KeywordsEthiopian airlinesAviation industryAir transportAirportsEfficiencyGrowthLabor useEthiopiaJEL ClassificationL93J01O4D24

The relationship between airport congestion and passenger delays at an airport is determined by many factors. Among these factors are scheduled and actual flight times, flight itineraries, airport capacity, and turn around time between flights. From the existing recorded data, it is possible to present a general profile of both airport congestion and passenger delays, measured with respect to the published schedule, at major airports within the US. This paper illustrates the discrepancy between the two measurements. Airport congestion may be masked by flight schedules which account for routine arrival delays and/or with slack time provided for turn around at an airport. It is possible for an airport to be heavily utilized, with little or unnoticeable at-gate delays (measured with respect to scheduled arrival time). On the other hand, at-gate delays can occur at under-utilized airports. Arrival and departure queuing delays are better indicators of airport congestion than passenger delays. Average flight at-gate delays are derived from performance data and compared with simulation results for 30 of the busiest airports in USA for a good weather day. The effects of variations in schedule flight time and slack time are studied parametrically in the simulation and calibrated to match the recorded baseline national airspace system (NAS) delay profiles. This paper illustrates a technique for estimating NAS-wide impact of propagated flight delays, based upon a method for calibration a system-level simulation against real world delays as well as delays derived from other simulations.

The arrangements regarding the legal protection of passengers and goods on the transport of air, is set out in legislation, agreements, and habits. The air transport law is keperdataan, the provision of air transport to be found in the laws of positive air in Indonesia are: Air Transportation Ordinance Stbl. 1939 No. 100, law No. 1 of 2009, and the Statute No. 8 1999. The responsibility of carrying on the safety of passengers and goods in the implementation of air transportation The principle of presumption of liability /presumtion of/ presumtion fault of negligence. The carrier is responsible for loss suffered by passengers or goods because the sender of a passenger wounded or killed, his baggage or damaged or lost, or damage to goods transfers and the delay in coming, while the principle of limitation of liability. The responsibility of the carrier is limited to a certain amount, this principle which encourages the carrier to resolve the problem by peaceful means. And the principle of absolute liability or strict liability. The carrier is considered to be always responsible without any possibility of freeing themselves unless the aggrieved innocent or were responsible for the losses on him. Compensation given by air carriers is a number of nominal value of money as a form of responsibility for accidents that caused deaths or injuries, lost baggage and flight delays. Legal efforts for passenger who feel or losses can file a lawsuit or claim to the airline, lawsuit or dispute settlement can be reached through two channels, namely the courts and lanes outside the court.

Air transportation is a mode of transportation that continues to grow rapidly in Indonesia, marked by the construction of new airports and the improvement of facilities at existing airports. However, flight delays remain one of the main issues faced by the aviation industry, including by Super Air Jet. This study aims to analyze the effect of flight delays on passenger satisfaction at Super Air Jet at Sultan Aji Muhammad Sulaiman Sepinggan International Airport, Balikpapan. The study used a quantitative approach involving 97 respondents who were Super Air Jet passengers. Data management was carried out through several stages of testing, namely instrument testing (validity and reliability), data quality testing (linearity, normality, and heteroscedasticity), and hypothesis testing using simple linear regression analysis, t-test, and coefficient of determination (R²) with the help of IBM SPSS Statistic 22 software. The results of the study indicate that flight duration has a significant effect on passenger satisfaction. This finding emphasizes the importance of improving service quality, especially in efforts to minimize delays, in order to maintain passenger trust in the airline. This study is expected to be a reference for Super Air Jet management in identifying the main causes of flight delays and developing effective strategies to improve passenger satisfaction.