Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Airline Customer Satisfaction: A Machine Learning and Causal Analysis Approach

Tejas Mirthipati

TL;DR

The paper tackles the problem of improving airline customer satisfaction in the post-pandemic era by linking service quality to revenue through the Service-Profit Chain. It jointly employs machine learning to predict satisfaction from survey and operational features and causal inference via the CausalLib package to estimate the causal impact of online boarding pass satisfaction on overall satisfaction, using inverse propensity weighting and the Horvitz-Thompson estimator. Key findings show that online boarding satisfaction has a substantial causal effect ($\hat{ATE} \approx 0.236$) on overall satisfaction, with in-flight wifi also significant but smaller ($\approx 0.139$). The results offer actionable recommendations for airlines, such as streamlining online boarding and providing complimentary wifi, enabling data-driven service improvements to enhance customer experience and competitiveness.

Abstract

This study explores the enhancement of customer satisfaction in the airline industry, a critical factor for retaining customers and building brand reputation, which are vital for revenue growth. Utilizing a combination of machine learning and causal inference methods, we examine the specific impact of service improvements on customer satisfaction, with a focus on the online boarding pass experience. Through detailed data analysis involving several predictive and causal models, we demonstrate that improvements in the digital aspects of customer service significantly elevate overall customer satisfaction. This paper highlights how airlines can strategically leverage these insights to make data-driven decisions that enhance customer experiences and, consequently, their market competitiveness.

Enhancing Airline Customer Satisfaction: A Machine Learning and Causal Analysis Approach

TL;DR

The paper tackles the problem of improving airline customer satisfaction in the post-pandemic era by linking service quality to revenue through the Service-Profit Chain. It jointly employs machine learning to predict satisfaction from survey and operational features and causal inference via the CausalLib package to estimate the causal impact of online boarding pass satisfaction on overall satisfaction, using inverse propensity weighting and the Horvitz-Thompson estimator. Key findings show that online boarding satisfaction has a substantial causal effect () on overall satisfaction, with in-flight wifi also significant but smaller (). The results offer actionable recommendations for airlines, such as streamlining online boarding and providing complimentary wifi, enabling data-driven service improvements to enhance customer experience and competitiveness.

Abstract

This study explores the enhancement of customer satisfaction in the airline industry, a critical factor for retaining customers and building brand reputation, which are vital for revenue growth. Utilizing a combination of machine learning and causal inference methods, we examine the specific impact of service improvements on customer satisfaction, with a focus on the online boarding pass experience. Through detailed data analysis involving several predictive and causal models, we demonstrate that improvements in the digital aspects of customer service significantly elevate overall customer satisfaction. This paper highlights how airlines can strategically leverage these insights to make data-driven decisions that enhance customer experiences and, consequently, their market competitiveness.
Paper Structure (45 sections, 4 equations, 19 figures, 1 table)

This paper contains 45 sections, 4 equations, 19 figures, 1 table.

Table of Contents

  1. Introduction
  2. Industry Context
  3. Problem Statement
  4. Research Objectives
  5. Service-Profit Chain
  6. Research Methodology
  7. Data Collection and Preprocessing
  8. Data Background
  9. Data Preprocessing
  10. Exploratory Data Analysis
  11. Age Distribution Analysis
  12. Customer Satisfaction by Travel Class
  13. Flight Delay Tolerance by Flight Length
  14. Loyalty Membership and Satisfaction
  15. Online Boarding and Departure/Arrival Time Satisfaction
  16. ...and 30 more sections

Figures (19)

  • Figure 1: Five-Year Stock Performance of Delta Air Lines (2020-2024).
  • Figure 2: The Service-Profit Chain Model Illustrating the Link between Service Quality and Revenue.
  • Figure 3: Snapshot of Raw Data
  • Figure 4: Box Plot of Arrival/Departure Delays Highlighting Outliers
  • Figure 5: Scatter Plot Illustrating Collinearity Between Two Predictors
  • ...and 14 more figures