The Impact of Machine Learning and Artificial Intelligence on Airline Revenue Optimization through Dynamic Pricing: A Case Study of American Airlines (1996–2023)

This thesis research investigates the impact of Machine Learning (ML), Artificial Intelligence (AI), and data analytics on airline revenue optimization through dynamic pricing. Situated in the airline and tourism industries, where demand is volatile and inventory is perishable, the study emphasizes how data-driven decision-making, demand forecasting, and pricing analytics can support more adaptive, efficient, and competitive pricing strategies. It also highlights dynamic pricing as an analytics-based approach in which fares can respond to changing market conditions, customer behavior, and increasingly real-time data inputs.

Using a longitudinal dataset covering the period from 1996 to 2023, the research applies empirical data analysis through time-series analysis, multivariate regression, and hypothesis testing to evaluate the relationship between AI adoption and airline revenue performance. The findings indicate a statistically significant increase in revenue in the post-2010 period, consistent with the broader integration of AI-, ML-, and analytics-driven pricing systems in the airline industry.

By connecting revenue management with machine learning, artificial intelligence, and data analytics, this study contributes long-term empirical evidence to the literature on digital transformation in aviation. It also underlines the growing strategic importance of analytical capabilities for pricing, forecasting, and decision-making, offering useful insights for researchers, industry practitioners, and future work in data-driven tourism and aviation management.