近年来,信用问题已成为全社会共同关注的一个重要话题.通过建立高校学生个人信用评价体系来引导和督促学生重视个人信用记录、改善个人信用行为、推动高校助学贷款、就业等各项工作的开展是非常必要的.采用PSO-BP算法建立模型,对BP算法进行优化,克服了BP神经网络收敛速度慢、易陷入局部极小、初始值难以确定等固有缺陷.通过在Matlab环境下进行仿真,结果表明,PSO-BP加快了BP的收敛速度,提高了BP韵泛化能力,PSO-BP模型的训练效果明显优于BP模型,在高校学生个人信用评价中具有一定的实践意义.%In recent years, credit issue has already become an important topic which is focused by the whole society. It is necessary to establish personal credit evaluation system for college students, which will help students be guided and supervised to attention their personal credit record, improve their personal credit behavior, also will promote the job of college student loans and employment etc. In this paper, we used PSO-BP algorithm to construct the model of personal credit evaluation for college students, which was used to optimize the BP neural network. It overcomes the inherent of BP, such as its convergence speed is slow, the result is easy into the local minimum, and initial parameters are difficult to determine. Through simulating by Matlab, it showed that PSO-BP accelerated the convergence speed, improved the generalization ability of BP model. PSO-BP model is obviously superior to BP model. PSO-BP model has certain practical significance in personal credit evaluation system for college students.
展开▼
