Using Artificial Fish Swarm Algorithm to Optimize Service Satisfaction Performance and Characteristic Model for Mainland Tourist in Taiwan

In this article, two groups of analysis results of grey relational analysis and SOM will be used by this article as dependent variables, and 9 question items of satisfaction will be used as independent variables to perform the construction of GRNN, meanwhile, newer AFSA and PSO will be used to adjust the parameters of GRNN so that the classification forecast capability can be enhanced. From the analysis result, it can be seen that although the convergence speed of RMSE of AFSA optimized GRNN model is slower, yet it can jump away from local minimal value, meanwhile, the classification forecast accuracy is also higher PSO optimized GRNN model and general GRNN model.