Enhancing Agents Decision Making Process in Multi agent Models of stock Market Using Fuzzy Open CLA
Financial market modeling using artificial agents as an emerging analytical approach which influences our view on the agents behavior and the market structure has grown rapidly in recent years. This research augments a Fuzzy Decision Making Process to an Open Cellular Learning Automata (OCLA) besides an Artificial Neural Network, as a basic framework to simulate a multi agent stock market It would be the first step to extend the ability of agents in portfolio management in uncertain financial market conditions. The simulation results can be employed in policy makings as well as providing agents perspective in some of the asymmetric information issues and expectations consequences. This study would eventually serve as an outstanding progress in finding a solution for the unwillingness of economists who look at stock market computational modeling as a black box with superior but uninterpretable results. Employing Open CLA, external variables are added to the model that provides the opportunity of estimating the effect of these variables, besides enhancing the chance of having a well simulated market. The result indicates that the system performance is close to the real market values with adequate training in advance.
Artificial Stock Market Fuzzy Cellular Learning Automata Neural Networks
Behrouz Bokharaeian Hamed M. Shafiee Hamed Alaei
Faculty of Computer Science and Information Technology University Putra Malaysia,Selangor, Malaysia Faculty of Economics and Management University Putra Malaysia,Selangor, Malaysia The Grove School of Engineering, The City College of New York, CUNY, NY, USA
国际会议
上海
英文
607-611
2011-03-11（万方平台首次上网日期，不代表论文的发表时间）