Dissertation Title: DYNAMIC PRICING AND REVENUE MANAGEMENT IN THE HOTEL SECTOR
Authors: Arjola SINANI
- Institution: University of Tirana, Faculty of Economics, Department of Statistics and Applied Informatics
- Field of study: Applied Statistics and Informatics / Applied Statistics and Mathematics in Economics
- Publication date: 08.07.2026
- The dissertation is published in Albanian.
© Copyright: Arjola SINANI
Published by the University of Tirana
Based on legal acts, regulations and policies of the UT
👉 Click here to view the full dissertation (PDF)
Abstract
This study addresses one of the central issues of contemporary management in the hospitality sector: the construction and empirical testing of an integrated dynamic pricing and revenue management framework, which links demand forecasting, price elasticity estimation and price optimization, taking into account demand uncertainty. The study is based on the premise that pricing decision-making in hospitality should not be treated as an isolated rate-setting process, but as a structured problem of capacity allocation and revenue maximization under conditions of seasonality, capacity constraints and variability in consumer behavior.
The aim of the thesis is to develop and test a single analytical architecture, in which demand forecasting, price elasticity and price optimization function as interconnected links of a single decision-making system. In terms of methodology, the study builds an integrated analytical process that starts with the processing of hotel operational data and their transformation into a panel at the day-of-stay level, continues with demand forecasting through a combined model approach, moves on to the estimation of price elasticity by hotel and distribution channel, and ends with price optimization through a mathematical model of mixed integer linear programming. Further, the model is extended with a more robust variant to uncertainty, with the aim of assessing not only expected revenues, but also the sustainability of pricing policies in alternative demand scenarios.
The empirical analysis is based on real data from three hotels in the city of Vlora. The results show that there is no single forecasting model that systematically dominates in all cases, which supports the use of a combined approach as a more appropriate solution to the heterogeneous nature of hotel demand. The study also confirms that the price elasticity is negative in all three hotels and that demand through online booking platforms is more elastic than direct demand, indicating that price sensitivity varies significantly according to the distribution channel. At the same time, the integration of these elasticities into the demand function for optimization shows that the statistically estimated parameters can be used consistently in the construction of operational pricing policies. The optimization results prove that the model produces prices that follow a reasonable economic logic, while the extended variant for handling uncertainty exhibits a stabilizing role against possible deviations of demand from the baseline scenario.
The main contribution of the thesis is in several aspects. On the theoretical level, it strengthens the argument that dynamic pricing and revenue management in the hospitality industry should be treated as an integrated system and not as a set of separate techniques. On the methodological level, the study proposes and tests a complete analytical framework that links demand forecasting, price elasticity and price optimization in a single process. On the empirical and practical level, the thesis brings evidence from the Albanian hospitality industry and shows that data-driven pricing systems can be both rigorously analytical and operationally applicable.
Keywords: dynamic pricing, revenue management, hotel industry, demand forecasting, price elasticity, price optimization, demand uncertainty, distribution channels, online booking platforms, Albanian hotel industry.
Abstract
This study addresses one of the central issues in contemporary hospitality management: the development and empirical testing of an integrated framework for dynamic pricing and revenue management that links demand forecasting, price elasticity estimation, and price optimization while explicitly accounting for demand uncertainty. The study is grounded in the premise that pricing decisions in the hotel sector should not be treated as an isolated tariff-setting process, but rather as a structured problem of capacity allocation and revenue maximization under conditions of seasonality, capacity constraints, and changing consumer behavior. The aim of the dissertation is to develop and test a unified analytical architecture in which demand forecasting, price elasticity, and price optimization operate as interconnected components of a single decision-making system. Methodologically, the study builds an integrated analytical process that begins with the preparation of hotel operational data and their transformation into a stay-day panel, continues with demand forecasting through a combined modeling approach, proceeds to the estimation of price elasticity by hotel and distribution channel, and concludes with price optimization through a mixed-integer linear programming model. The framework is further extended with a more uncertainty-sensitive variant in order to evaluate not only expected revenue, but also the stability of pricing policies under alternative demand scenarios.
The empirical analysis is based on real data from three hotels located in the city of Vlora. The findings show that no single forecasting model systematically dominates across all cases, which supports the use of a combined approach as a more suitable solution for the heterogeneous nature of hotel demand. The study also confirms that own-price elasticity is negative across all three hotels and that demand through online travel agencies is more elastic than direct demand, indicating that price sensitivity differs substantially across distribution channels. At the same time, the integration of these elasticity estimates into the demand function for optimization demonstrates that statistically estimated parameters can be used consistently in the construction of operational pricing policies. The optimization results show that the model generates prices that follow an economically sound logic, while the extended uncertainty-oriented variant plays a stabilizing role against possible deviations of actual demand from the baseline scenario.
The main contribution of the dissertation is threefold. At the theoretical level, it strengthens the argument that dynamic pricing and revenue management in hospitality should be treated as an integrated system rather than as a collection of separate techniques. At the methodological level, the study proposes and tests a complete analytical framework that links demand forecasting, price elasticity, and price optimization within a single process. At the empirical and practical level, the dissertation provides evidence from the Albanian hospitality sector and shows that data-driven pricing systems can be both analytically rigorous and operationally applicable.
Keywords: dynamic pricing, revenue management, hospitality, demand forecasting, price elasticity, price optimization, demand uncertainty, distribution channels, online travel agencies, Albanian hospitality sector.