RevenuePilot: Operationalizing Agentic AI for Airline Revenue Management at Scale
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V7I1P135Keywords:
Airline Revenue Management, Agentic AI, Large Language Models, Dynamic Pricing, Inventory Control, Demand Forecasting, Multi-Agent Systems, EMSR, Real-Time OptimizationAbstract
Airline revenue management (RM) represents one of the most complex real-time optimization challenges in commercial operations, requiring simultaneous decisions across pricing, inventory allocation, and demand forecasting under significant uncertainty. Traditional RM systems, while mathematically sophisticated, struggle to adapt to rapidly changing market conditions, competitive dynamics, and emerging disruptions. This paper presents RevenuePilot, an agentic AI system that operationalizes large language model capabilities for airline revenue management at scale. RevenuePilot employs a multi-agent architecture with specialized agents for dynamic pricing optimization, inventory control, demand forecasting, and overbooking management, coordinated through a central orchestration layer. We evaluate RevenuePilot on a major airline’s domestic network, demonstrating a 4.2% improvement in revenue per available seat mile (RASM), 12% reduction in spoilage, and 8% decrease in denied boardings compared to the incumbent Expected Marginal Seat Revenue (EMSR) system. Our results show that agentic AI can effectively augment traditional optimization approaches while providing explainability and adaptability critical for operational deployment.
Downloads
References
[1] K. Talluri and G. Van Ryzin, “The Theory and Practice of Revenue Management,” Springer Science & Business Media, 2004.
[2] L. R. Weatherford and S. E. Bodily, “A taxonomy and research overview of perishable-asset revenue management: Yield management, overbooking, and pricing,” Operations Research, vol. 40, no. 5, pp. 831-844, 1992.
[3] P. P. Belobaba, “Application of a probabilistic decision model to airline seat inventory control,” Operations Research, vol. 37, no. 2, pp. 183-197, 1989.
[4] K. Littlewood, “Forecasting and control of passenger bookings,” Airline Group International Federation of Operational Research Societies Proceedings, vol. 12, pp. 95-117, 1972.
[5] K. Talluri and G. Van Ryzin, “An analysis of bid-price controls for network revenue management,” Management Science, vol. 44, no. 11, pp. 1577-1593, 1998.
[6] E. L. Williamson, “Airline network seat inventory control: Methodologies and revenue impacts,” Ph.D. dissertation, Massachusetts Institute of Technology, 1992.
[7] J. I. McGill and G. J. Van Ryzin, “Revenue management: Research overview and prospects,” Transportation Science, vol. 33, no. 2, pp. 233-256, 1999.
[8] B. Vinod, “Evolution of yield management in travel,” Journal of Revenue and Pricing Management, vol. 15, no. 3-4, pp. 203-211, 2016.
[9] L. R. Weatherford, “The history of forecasting models in revenue management,” Journal of Revenue and Pricing Management, vol. 15, no. 3-4, pp. 212-221, 2016.
[10] L. R. Weatherford and S. Kimes, “A comparison of forecasting methods for hotel revenue management,” International Journal of Forecasting, vol. 19, no. 3, pp. 401-415, 2003.
[11] C. Chen et al., “Deep learning for airline revenue management,” Journal of Revenue and Pricing Management, vol. 19, no. 4, pp. 234-248, 2020.
[12] R. Rana and F. S. Oliveira, “Real-time dynamic pricing in a non-stationary environment using model-free reinforcement learning,” Omega, vol. 47, pp. 116-126, 2014.
[13] Y. Zhang et al., “Transformer-based demand forecasting for airline revenue management,” Transportation Research Part E, vol. 158, 102589, 2022.
[14] S. Yao et al., “ReAct: Synergizing reasoning and acting in language models,” in Proc. ICLR, 2023.
[15] L. Wang et al., “A survey on large language model based autonomous agents,” arXiv preprint arXiv:2308.11432, 2024.
[16] Agarwal, S. (2025). AI-Augmented Social Media Marketing: Data-Driven Approaches for Optimizing Engagement. International Journal of Emerging Research in Engineering and Technology, 6(2), 15-23. https://doi.org/10.63282/3050-922X.IJERET-V6I2P103.
