Social Networking and Information Diffusion in Automated Markets
To what extent do networks of influence between market traders impact upon their individual performance and the performance of the specialists in which they operate? Such a question underpins the content of this study, as an investigation is conducted using the JCAT double auction market simulation platform, developed as a part of the CAT Market Design Tournament. Modifications to the JCAT platform allow for influential networks to be established between traders, across which they transmit information about their trading experiences to their connected peers. Receiving traders then use this information (which is the product of an n-armed bandit selection algorithm) to guide their own selection of market specialist and trading strategy. These modifications give rise to a sequence of experimental tests, the documented results of which provide an answer to the question phrased above. Analysis of the results shows the benefits of taking advice as a collective and demonstrates the properties of the communities which emerge as a result of engaging in widespread social contact.
KeywordsJCAT CAT agent-based trading social networking agent-based simulation automated trading
Unable to display preview. Download preview PDF.
- 2.Cai, K., Gerding, E., McBurney, P., Niu, J., Parsons, S., Phelps, S.: Overview of CAT: A market design competition (version 2.0), Technical Report ULCS-09-005, Department of Computer Science, University of Liverpool, Liverpool, UK (2009)Google Scholar
- 7.Huynh, T.D., Jennings, N.R., Shadbolt, N.R.: Fire: An integrated trust and reputation model for open multi-agent systems. In: ECAI, vol. 16, pp. 18–22 (2004)Google Scholar
- 11.Mahdi, K., Torabi, S., Safar, M.: Diffusion and Reverse Diffusion Processes in Social Networks: Analysis using the Degree of Diffusion alpha. In: Proceedings of the 3rd IEEE International Conference on Ubi-media Computing, U-Media (US) (May 2010)Google Scholar
- 12.McKean, J., Shorter, H., Luck, M., McBurney, P., Willmott, S.: Technology diffusion: the case of agent technologies. AAMAS 17(3), 372–396 (2008)Google Scholar
- 14.Niu, J., Cai, K., Parsons, S., McBurney, P., Gerding, E.: What the 2007 TAC Market Design Game tells us about effective auction mechanisms. AAMAS 21(2), 172–203 (2010)Google Scholar
- 15.Robinson, E., McBurney, P., Yao, X.: Market niching in multi-attribute computational resource allocation systems. In: Kettler, W., Lang, K.R., Lee, K.J. (eds.) Proceedings of the 13th International Conference on Electronic Commerce (ICEC 2011), Liverpool (August 2011)Google Scholar
- 17.Sutton, R.S., Barto, A.G.: An n-armed bandit problem. In: Reinforcement Learning: An Introduction (Bradford, ed.), pp. 2.1–2.2. The MIT Press, Cambridge (2005)Google Scholar
- 18.Vytelingum, P., Vetsikas, I.A., Shi, B., Jennings, N.R.: IAMwildCAT: The winning strategy for the TAC Market Design Competition. In: Proceedings of 18th European Conference on Artificial Intelligence, Patras, Greece, pp. 428–434 (2008)Google Scholar
- 19.Zhou, J., Zhou, C., Wang, J., Qi, L., Huang, W.: Detection of clusters and outlying nodes in spatial networks. In: Geoinfomatics 2008 and Joint Conference on GIS Built Environment, vol. 7147(1), pp. 1–8 (2008)Google Scholar