Artificial economic life: a simple model of a stockmarket
Proceedings of the NATO advanced research workshop and EGS topical workshop on Chaotic advection, tracer dynamics and turbulent dispersion
PARA '02 Proceedings of the 6th International Conference on Applied Parallel Computing Advanced Scientific Computing
Complex energy landscape mapping by histogram assisted genetic algorithm
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Adaptive genetic algorithm and quasi-parallel genetic algorithm: application to knapsack problem
LSSC'05 Proceedings of the 5th international conference on Large-Scale Scientific Computing
EvoApplications'12 Proceedings of the 2012t European conference on Applications of Evolutionary Computation
Spatial and temporal resource allocation for adaptive parallel genetic algorithm
UC'07 Proceedings of the 6th international conference on Unconventional Computation
| Hi-index | 0.00 |
The effect of random news on the performance of adaptive agents as investors in stock market is modelled by genetic algorithm and measured by their portfolio values. The agents are defined by the rules evolved from a simple genetic algorithm, based on the rate of correct prediction on past data. The effects of random news are incorporated via a model of herd effect to characterize the human nature of the investors in changing their original plan of investment when the news contradicts their prediction. The random news is generated by white noise, with equal probability of being good and bad news. Several artificial time series with different memory factors in the time correlation function are used to measure the performance of the agents after the training and testing. A universal feature that greedy and confident investors outperform others emerges from this study.