Combinatorial Aspects of Yield Management, a Reinforcement Learning Approach


B. Martin
Analytical and Stochastic Modelling Techniques and Applications ASMTA'04, Magdeburg, Germany, 2004.
 
Back to my home page ...
Back to my publication page ...
 
  • Yield management is an important issue for television advertising. Anyway, the major part of the research in revenue management focus on the airline or hotel industry. The TV advertising case has some specificities, where the most important is the decomposition of the offer into a lot of small TV breaks (about 10 spots only). The aim of this article is to understand how this change the optimization policy and propose generic solutions based on simulations and approximate dynamical programming.

  •  
  • Keywords: Television advertising, multi-knapsack, Monte-Carlo, aproximate dynamical programming, revenue management.

  •  
    Download (gzipped postscript)
     
    @InProceedings{marasmta04,
             author = {B. Martin},
             title = {Combinatorial Aspects of Yield Management, a Reinforcement Learning Approach},
             booktitle = {Proceedings of The 2004 European Simulation and Modelling Conference ESM2004},
             year = {2004}
             address = {Magdeburg, Germany}
             month = {June}
    }