Forecasting Airline Customer Satisfaction through the Application of Diverse Machine Learning Algorithms

Airline customer satisfaction encapsulates passengers’ overall happiness with an airline’s services, spanning aspects like booking, in-flight experience, and customer service. It is a crucial metric for airline success, influencing brand loyalty and reputation. Achieving and maintaining high customer satisfaction is integral to airlines’ competitiveness and long-term viability in the dynamic aviation industry. This study examines a dataset comprising 129,880 customer records within the airline industry, subjecting it to evaluation by machine learning models, including logistic regression, decision tree, and random forest. Among these, the random forest model stands out, yielding the most favorable results with an accuracy exceeding $94 \%$. This outcome emphasizes the efficacy of employing advanced machine learning techniques for precise predictions in the domain of airline customer satisfaction.