Preana: Game Theory Based Prediction with Reinforcement LearningReportar como inadecuado

Preana: Game Theory Based Prediction with Reinforcement Learning - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Inthis article, we have developed a game theory based prediction tool, namedPreana, based on a promising model developed by Professor Bruce Beuno deMesquita. The first part of this work is dedicated to exploration of thespecifics of Mesquita’s algorithm and reproduction of the factors and featuresthat have not been revealed in literature. In addition, we have developed alearning mechanism to model the players’ reasoning ability when it comes totaking risks. Preana can predict the outcome of any issue with multiplesteak-holders who have conflicting interests in economic, business, andpolitical sciences. We have utilized game theory, expected utility theory, Medianvoter theory, probability distribution and reinforcement learning. We were ableto reproduce Mesquita’s reported results and have included two case studiesfrom his publications and compared his results to that of Preana. We have alsoapplied Preana on Irans 2013 presidential election to verify the accuracy ofthe prediction made by Preana.


Game Theory, Predictive Analytics, Reinforcement Learning

Cite this paper

Eftekhari, Z. and Rahimi, S. 2014 Preana: Game Theory Based Prediction with Reinforcement Learning. Natural Science, 6, 1108-1121. doi: 10.4236-ns.2014.613099.

Autor: Zahra Eftekhari, Shahram Rahimi



Documentos relacionados