Hybrid Algorithm for Ticket Reservation Process in Passenger Rail Transport

Dragana Macura, Milica Selmić, Dušan Teodorović, Milutin Milošević

Last modified: 2017-02-28


Managing tickets reservation process in passenger rail transport is complex task. For solving this kind of task, we develop a hybrid algorithm based on Artificial Neural Network and Payoff table as a decision support tool. The aim of the proposed algorithm is to suggest real time decisions about seat inventory allocations taking into account information from the past. The paper considers the revenue management application in passenger rail transport with variable capacity of sleeping cars. Uncertainty of available capacity is embedded in developed algorithm by Payoff table, while Artificial Neural Network is used as a tool for making real time decisions. We consider nested reservation system, and the algorithm is tested on hypothetical dana.


Revenue management; Rail transport with variable capacity; Artificial Neural Network; Payoff table

Full Text: PDF