Airline Passenger Satisfaction Analysis

Project Overview

This project presents an explanatory analysis of airline passenger satisfaction, utilizing a dataset that contains information about various aspects of the passengers’ travel experience. Through the exploration of predictive models and different machine learning techniques, we developed a KNIME workflow designed to help users better understand the variables influencing customer satisfaction and to identify key factors that can enhance the travel experience.

The aviation industry today increasingly emphasizes customer experience as a central element for the success of airlines. In a competitive market sector, every company must view passenger satisfaction as a critical indicator of the quality of service offered, as it is a key factor in customer loyalty and brand reputation.

Goal

This project aims to provide valuable insights into passenger satisfaction within the aviation industry. By identifying key factors that influence customer ratings, airlines can enhance their services, leading to increased customer loyalty and improved brand reputation.

Dataset

The analysis focuses on a comprehensive dataset containing detailed information on passengers’ in-flight experiences. This dataset comprises variables that reflect different aspects of the passenger journey, such as:

• Customer ratings of flight experiences (on a scale of 1 to 5)
• Demographic information (age, gender)
• Flight class purchased
• Customer loyalty status

The dataset is sourced from Kaggle and can be accessed at the following link: Airlines Customer Satisfaction Dataset. It uses data collected by a company with a fictitious name, Invistico, to protect passenger privacy and includes customer details and feedback on various flight aspects.

Objectives

The main objective of this project is to develop predictive models capable of anticipating passenger satisfaction levels. These models will be used to formulate recommendations aimed at improving the overall customer experience.

Methodology

The project follows a systematic approach, including:

1. Data Collection: Gathering and preprocessing the dataset.
2. Exploratory Data Analysis: Understanding patterns and insights from the data.
3. Model Development: Implementing various machine learning techniques to build predictive models.
4. Recommendations: Analyzing the results to suggest improvements in customer experience.