PREDICTING AIRLINE PASSENGER SATISFACTION USING RAPID MINER AND ML ALGORITHMS

Airline passenger satisfaction is a critical factor that impacts the success and reputation of an airline. Therefore, accurately predicting passenger satisfaction can provide valuable insights for airlines to improve their services and enhance customer experience. With the increasing availability of data, airlines can leverage machine learning techniques to analyse passenger satisfaction and make data-driven decisions to improve their services. This study uses decision trees and random forest algorithms in R and rapid miner to predict airline passenger satisfaction. The dataset used in this study contains a variety of features related to airline services, such as flight delays, seat comfort, in-flight entertainment, and customer service ratings. The dataset will be pre-processed to handle missing values, outliers, and categorical variables. The dataset is divided into train and test sets and models are applied. The findings will shed light on the factors that significantly impact passenger satisfaction and provide actionable insights for airlines to improve their services and enhance customer experience.