An Agent-Based Approach to the Dynamic Price Problem

Agent and Multi-Agent Systems: Technologies and Applications: 5th KES International Conference (KES-AMSTA 2011) 2011
Jurijs Čižovs

This paper focuses on the agent realisation of the Markov Decision Process in the dynamic price problem. The use of MDP is caused by the properties of the trade system under consideration. Due to exploiting data mining tools, time series processing, clustering and other operations, the obtained interaction architecture has turned to be overloaded. Taking into account particular properties of the considered trade system as well as its model, which is MDP-based, this paper suggests a novel specific multiagent technique for MDP system realisation.

Keywords
Artificial Intelligent Agents, Markov Decision Processes, Dynamic Pricing Policy
DOI
10.1007/978-3-642-22000-5_46
Hyperlink
http://link.springer.com/chapter/10.1007%2F978-3-642-22000-5_46

Čižovs, J. An Agent-Based Approach to the Dynamic Price Problem. In: Agent and Multi-Agent Systems: Technologies and Applications: 5th KES International Conference (KES-AMSTA 2011), United Kingdom, Manchester, 30 Jun-1 Jul., 2011. Berlin: Springer-Verlag Berlin, 2011, pp.446-455. ISBN 978-3-642-21999-3. e-ISBN 978-3-642-22000-5. ISSN 0302-9743. Available from: doi:10.1007/978-3-642-22000-5_46

Publication language
English (en)