首页 | 新闻公告 | 投稿须知 | 编委会 | 关于杂志 | 订阅 | 留言FAQ | 广告服务 | 相关链接 | 下载区 | 联系我们

实证驱动的移动银行用户行为定性模拟及优化研究
Empirical relationship driven qualitative simulation on Mobile Bank User Adoption Behavior and optimization study
摘要点击 4586  全文点击 0  投稿时间:2011-01-14  修订日期:2011-10-31
  查看/发表评论  下载PDF阅读器
中文关键词  用户使用行为;优化;QSIM;实证研究;BP神经网络
英文关键词  user adoption behavior; optimization; QSIM; empirical study; BP neural network
基金项目  国家自然科学基金项目(面上项目,重点项目,重大项目)
作者单位E-mail
危小超 华中科技大学 weixiaochaowin@163.com 
中文摘要
      以最小化移动银行营销费用、最大化用户使用行为为优化目标,建立可描述一般性受当前影响因素状态约束的移动银行用户使用行为决策问题的优化模型,并提出实证关系驱动的定性模拟方法对模型进行求解。以移动银行使用意愿影响因素为研究对象,设计了问卷,使用SPSS的统计分析以及结构方程模型得到影响因素之间的关系。通过QSIM算法驱动因素间交互关系的动态演化,结合BP神经网络训练目标函数,从而寻找用户行为趋于稳定时的最佳决策变量组合,并利用波动—均衡现象,验证了模型的合理性。算例分析表明了该模型和算法的有效性,能为移动银行推广的实时优化决策提供支持,同时结果显示:商家声誉和感知风险对用户使用意愿影响显著,但感知风险影响程度已经降低。
英文摘要
      The optimization model for mobile bank user adoption behavior decision problem with constraint of current state of influencing factors is developed, in which the objective function was to minimize the bank marketing cost and maximize user adoption behavior. Driven by empirical relationships data, qualitative simulation is created as a solution. BP neural network was used to train objective function. QSIM algorithm was used to drive dynamic evolution of the interaction between the variables to get the optimal variable combination. Model was validated by oscillation-equilibrium phenomenon, which contributes some decision support for real-time optimization of user's behavior. The results show that except standard habit, corporate reputation and perceived risk had significant effect on user acceptance, though the impact of perceived risk has been reduced.
关闭

版权所有 © 2007 《系统工程学报》
通讯地址:天津市卫津路92号天津大学25教学楼A区908室 邮编:300072
联系电话/传真:022-27403197 电子信箱: jse@tju.edu.cn