一种基于径向基网络的读者流失分析模型  

A Prediction Model of Reader Loss Analysis Based on RBF NN

作　　者：聂珍[1] 

机构地区：[1]双矽重庆理工大学图书馆,重庆400050

出　　处：《现代情报》2010年第6期27-30,共4页Journal of Modern Information

基　　金：重庆自然科学基金项目《递归RBF网络研究与应用》(合同编号2007BB2406)

摘　　要：大量而频繁的读者流失导致了图书馆知识服务范围的减少,降低了图书馆信息服务的质量。本文根据读者资料和借阅行为及其相关数据等历史信息,将径向基神经网络应用于读者流失分析中,针对目前图书借阅中存在的问题,给出了读者流失预测模型,利用训练后的模型对读者的流失率进行预测并生成读者列表。该模型通过试验运行,取得了良好的效果,对大学图书馆的服务策略实施具有现实的指导意义。Large and frequent loss of readers has led to the range reduction of library knowledge services,and reduced the quality of library information services.According to historical data of reader information and borrow behaviour,a certain RBF neural networks has been applied to reader loss analysis.For the problems existing in current reseach,a reader loss prediction model has been established.The loss probability of each reader has been computed by the model and possible loss reader list is recorded.The prediction model gets a satified results in the experimental test,which can be used to guide the service strategy of a university library.

关 键 词：读者流失 信息服务 预测模型 径向基网络 

分 类 号：G250.71[文化科学—图书馆学] TP183[自动化与计算机技术—控制理论与控制工程]