Kannapha AmaruchkulMurati Soomboon2022-04-122022-04-122016b192974https://repository.nida.ac.th/handle/662723737/5727Thesis (Ph.D. (Applied Statistics))--National Institute of Development Administration, 2016In this study, a two- class revenue management ( RM) model, which combines two of the most important RM strategies for a passenger airline: overbooking and seat inventory control is proposed. Using this model, it is possible to concurrently find both the optimal booking limit and the optimal overbooking limit. Consequently, on a closed- form expression for an optimal booking/ overbooking limit, sensitivity analysis was analytically assessed by changing model parameters such as revenue, the penalty cost associated with unsatisfied demand, the show- up probability, refunds, denied boarding cost, and plane capacity, and a study of its properties and expected profit function carried out.Numerical studies were carried out in two parts. The first part was performed to check the results of the sensitivity analysis using simulated data and the second to evaluate the performance of the proposed model using real-life data. Finally, three hypotheses were tested using real-life data. 5,184 sets of conditions were used to check the result of the sensitivity analysis, the properties of the optimal booking/overbooking limit, and the expected profit function. It was concluded that the booking limit is affected by the demand for class 1 seat allocations and all model parameters except for denied boarding cost and overbooking limit is affected by all of the model parameters for class 2 seat allocations, including denied boarding cost and capacity. Using real-life data, the performance of the policy from the proposed model was evaluated against the fixed-booking limit policy of an airline and was found to outperform it. Moreover, three hypotheses: the effect of varying the number of update booking limit points, the effect of an incorrect initial mean for demand, and the effect of a number of smoothing constants on an exponential smoothing method were tested using real-life data. At the 0.05 significance level, it was found that different numbers of update booking limit points affected profit, incorrect initial mean for demand did not affect profit when a high number of update booking limit points was set, and all of the smoothing constants in exponential smoothing method affected profit to some extent.116 leavesapplication/pdfengThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.Stochastic processesMathematical optimizationOperations researchRevenue managementtext--thesis--doctoral thesis10.14457/NIDA.the.2016.100