A Multilayer Perceptron Neural Network with Selective-Data Training for Flight Arrival Delay Prediction

Abstract

Flight delay is the most common preoccupation of aviation stakeholders around the world. Airlines, which suffer from a monetary and customer loyalty loss, are the most affected. Various studies have attempted to analyze and solve flight delays using machine learning algorithms. This research aims to predict flights’ arrival delay using Artificial Neural Network (ANN). We applied a MultiLayer Perceptron (MLP) to train and test our data. Two approaches have been adopted in our work. In the first one, we used historical flight data extracted from Bureau of Transportation Statistics (BTS). The second approach improves the efficiency of the model by applying selective-data training. It consists of selecting only most relevant instances from the training dataset which are delayed flights. According to BTS, a flight whose difference between scheduled and actual arrival times is 15 minutes or greater is considered delayed. Departure delays and flight distance proved to be very contributive to flight delays. An adjusted and optimized hyperparameters using grid search technique helped us choose the right architecture of the network and have a better accuracy and less error than the existing literature. The results of both traditional and selective training were compared. The efficiency and time complexity of the second method are compared against those of the traditional training procedure. The neural network MLP was able to predict flight arrival delay with a coefficient of determination R 2 of 0.9048, and the selective procedure achieved a time saving and a better R 2 score of 0.9560. To enhance the reliability of the proposed method, the performance of the MLP was compared with that of Gradient Boosting (GB) and Decision Trees (DT). The result is that the MLP outperformed all existing benchmark methods.

Cable fault classification in ADSL copper access network using machine learning

“…The multilayer perceptron algorithm takes the longest training time to classify the data based on its impairment type, which takes 3.74s to train 10-fold cross-validation. Training of MLP can be a bit of a gradual process [29] because the number of training epochs and time elapsed for total epochs indicates when the training was completed [30]. The result of classifications done using WEKA in Table 4 indicates that's random forest algorithm gives a promising result for the application of classifying fault types in ADSL copper access networks.…”

Impact of Aircraft Performance and Time of the Day on Flight Arrival Delays Prediction in the United States: a Machine Learning Classification

“…Furthermore, a failure in turnaround process caused by push-back, fueling/refueling, catering or mechanical check operations may engender delays. Personnel stress and fatigue [19] or personnel labor strike [21] are considered contributive to carrier traffic delays.…”

“…If it is higher, the flight is likely to be late. [21] concluded that the longer is the distance, the higher is the delay. Departure Delay Departure delays are contributive to arrival delays.…”

“…[22] claimed that congestion at destination airport is mostly originated at the departure airport. A traffic experiencing a delay on departure may be also delayed on arrival [21]. Hence, departure delay is a relevant feature to our study.…”

Social ski driver conditional autoregressive-based deep learning classifier for flight delay prediction

“…Nowadays, an increase in air traffic and flight delays has become a severe and prominent issue globally [1]. Based on the United States (US) Bureau of Transportation Statistics (BTS) report, most airline flights arrived 15 min late at their destination [14][15][16][17][18][19][20][21][22], thus incurring a loss of $30 billion, which is a challenge to the air transportation system [14,23]. Delay analyses have become an important research topic, and delay prediction has been the subject of earlier studies [14,24,25].…”