Algorithmic Crisis Recovery (ACR): A Human-in-the-Loop AI Framework for Operational Cost-Containment and Demand Stabilization During Black Swan Events

Nugawela, N.P. Gayan (2026): Algorithmic Crisis Recovery (ACR): A Human-in-the-Loop AI Framework for Operational Cost-Containment and Demand Stabilization During Black Swan Events.

Abstract

Abstract:

Purpose: This study aims to explain the key shortcomings of traditional RMS systems during Black Swan events. Whereas RMS models based on past trends tend to work well when the market is stable, they create what is called the "race to the bottom" effect in a crisis state by reducing rates in markets that have a price elasticity of zero. To solve these problems, an algorithmic crisis recovery (ACR) approach is introduced in this paper.

Methodology: Unlike conventional commercial applications, the ACR system incorporates the HITL approach, which allows the use of live data provided by Building Management Systems (BMS), HRIS platforms, and other live information in making revenue decisions. Its efficiency was proven using both a simulated case study and practical implementation insights from a five-star resort in Oman.

Findings: Three main aspects of the algorithmic strategy were identified: the Algorithmic Kill Switch, allowing for consolidation of zonal resources; the Human Capital Matrix for labor retention and cascading; and Crisis Survival Floor not determined by competitor panic but by the level of variable costs. According to the results, a shift in AI's role from a profit maximizer to an effective diagnostic tool can protect GOPPAR, maintain hotel brand integrity, and speed up the recovery process.

Practical Implications: This study provides revenue managers with an opportunity to mathematically justify rejecting bookings and consolidating their operations. As such, the new framework connects pricing decisions with facility management and promotes the transformation of a facility into a strategic asset.

• Item Type: MPRA Paper
• Language: English
• Keywords: Algorithmic Crisis Recovery, Human-in-the-Loop, Artificial Intelligence, Revenue Management, RevPAR, TRevPOR, GOPPAR, Cost-Containment, Demand Stabilization, Black Swan Events, Hospitality Optimization
• Subjects: L - Industrial Organization > L8 - Industry Studies: Services > L83 - Sports ; Gambling ; Restaurants ; Recreation ; Tourism; M - Business Administration and Business Economics ; Marketing ; Accounting ; Personnel Economics > M1 - Business Administration > M10 - General; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O33 - Technological Change: Choices and Consequences ; Diffusion Processes

References

References:

•Anderson, C. K. (2009). The price of discounting in low market conditions. Cornell Hospitality Quarterly, 50(1), 82-92. It focuses on the long-term damage caused by aggressive price cuts during crises. •Chen, J., & Smith, W. (2023). Integrated hospitality technology: Bridging the gap between BMS and RMS for operational efficiency. International Journal of Hospitality Management, 108, 103-115. Supports the need for API integration and breaking technical silos. •Enz, C. A., & Canina, L. (2010). Price management in the hospitality industry: The impact of pricing on revenue and market share during economic cycles. Journal of Revenue and Pricing Management, 9(3), 212-227. The foundational text for protecting brand equity and avoiding the "race to the bottom." •Gabor A., & Viglia, G. (2023). Human-in-the-loop: The future of algorithmic decision-making in hospitality revenue management. Journal of Travel Research, 62(4), 855-870. Justifies your HITL architecture and the ethical importance of the human revenue manager. •Ivanov, S., Webster, C., & Seyitoğlu, G. (2022). Crisis revenue management: A conceptual framework for survival and recovery. International Journal of Contemporary Hospitality Management, 34(7), 2561-2582. The primary source for the Crisis Survival Floor and recovery velocity theories. •Kimes, S. E. (2008). Hotel revenue management: A 20-year perspective. Cornell Hospitality Quarterly, 49(3), 267-276. Provides the historical context for the RGI, MPI, and ARI indexing. •Taleb, N. N. (2007). The Black Swan: The Impact of the Highly Improbable. New York: Random House.