An Improved ANN Algorithm and Its Application on Comprehensive Competitiveness Evaluation in E- Commerce Enterprises

摘要：

With the rapid development of E-commerce, the competition among E-commerce enterprises becomes more and more intense. To evaluate the comprehensive competitiveness of E-commerce enterprises scientifically and accurately, this paper proposes an improved artificial neural network (ANN) imports the adjustable activation function and LevenbergMarquardt optimization algorithm. The improved model not only simulate the expert in evaluating the comprehensive competitiveness and avoiding the subjective mistakes in the evaluation process, but also enhance the learning accuracy and the algorithm convergence speed greatly. The comprehensive competitiveness of 12 E-commerce enterprises in Beijing City shows that the improved model is stable and reliable.

关键词： Improved Artificial Neural Network Comprehensive Competitiveness Evaluation Model E-commerce Enterprises

作者: Qingwei Duan Jinliang Zhang Zhibin Liu

作者单位: College of Economics and Trade Agricultural University ofHebei Baoding City, Hebei Province, China Department of Economics and Management North China Electric Power University Baoding City, Hebei Pro

会议类型: 国际会议

会议名称: 2010 Second Asia-Pacific Conference on Information Processing(2010年第二届亚太地区信息处理国际会议 APCIP 2010)

会议地点: 南昌

会议语种:英文

页码: 611-614

在线出版日期: 2010-09-17（万方平台首次上网日期，不代表论文的发表时间）