Prediction of US airline passenger satisfaction using machine learning algorithms

Abstract

Due to the COVID-19 pandemic, the U.S. financial system and economy have also been severely affected. The U.S. airline industry has been hit particularly hard by the COVID-19 pandemic. Additionally, the aviation industry is also full of competition. One of the ways to attract customers and compete with other airline companies is by improving their service quality. Therefore, this study aims to predict the satisfaction of airlines based on the machine learning model and discover which features are more correlated with the target variable. In this study, the dataset consists of 129,880 observations and 1 target, 22 features or attributes (not including the identification). In this study, the result showed that the features that slightly correlate more with customer satisfaction are 'Online boarding', 'Inflight entertainment', 'Seat comfort', 'On-board service', 'Leg room service', 'Cleanliness', 'Flight Distance' and 'Inflight wifi service'. Then, K-Nearest Neighbors (KNN), Decision Tree Classifier (DTC), Logistic Regression (LR), Random Forest (RF), Naïve Bayes (NB) and AdaBoost were used to build the classification models. Data cleaning, exploratory data analysis, feature selection and One Hot Encoding were also performed before building the models. Finally, the models were evaluated based on their accuracy, precision, recall and F1-score. The results suggest that the champion model for this study is Random Forest, which achieved 89.20% accuracy, 93.04% precision and 88.80% F1-score. The results of this study can be used as a guide in applying machine learning to predict the satisfaction of airline passengers. This can also contribute to attracting passengers by improving the airline service quality.

Do We Scapegoat The Pandemic? Investigating The Changes in Satisfaction Drivers of Air Passengers With DWLS-SEM

“…Based on the goodness-of-fit indices, it is clear that the model is fit (CFI= 1.000; TLI= 1.000; RMSEA= 0.000; SRMR= 0.000). The results of the free model indicate that all service attributes have a statistically significant impact on overall passenger satisfaction in the pre-pandemic era, in line with the literature (Atalay et al, 2019;Ban & Kim, 2019;Brochado et al, 2019;Hong et al, 2023;Šebjan et al, 2017;Siering et al, 2018;Tahanisaz & Shokuhyar, 2020). Value for money, stressed by 121 Rajaguru (2016) as an indispensable factor for airlines to survive, has the highest impact, based on the coefficients.…”

“…So, all hypotheses are supported by the aggregated model. Thus, our findings are consistent with the literature (An & Noh, 2009;Atalık et al, 2019;Hong et al, 2023;Kim & Park, 2017;Siering et al, 2018). It is an anticipated consequence that passengers prioritize value for money as the primary driver of satisfaction, in line with Rajaguru (2016).…”

“…Hence, this service might gain new customers for the company (Byun & Lee, 2016). This service is correlated with passenger satisfaction (Hong et al, 2023), provided that its connection and speed have to be at least acceptable (Gao et al, 2021). Hence, we propose the hypothesis as follows:…”