基于Bass-BP组合模型的微信扩散研究  

Research on Diffusion of Wechat Based on Bass-Bp Combination Model

作　　者：蒋亚萍[1] JIANG Ya-ping(Shanghai Normal University Tianhua College, Shanghai 201815, China)

机构地区：[1]上海师范大学天华学院

出　　处：《数学的实践与认识》2018年第9期253-259,共7页Mathematics in Practice and Theory

摘　　要：微信扩散具备非线性变化特征，仅采纳单一预测算法无法有效描述微信扩散的规律．因此，提出了Bass—BP扩散组合模型．首先利用经典Bass模型对微信数据进行初步预测，再利用BP神经网络对Bass模型预测结果进一步非线性逼近．结果表明，Bass—BP组合模型相较于Bass经典模型和BP神经网络这两种单一的预测模型，具有更好的预测效果．Wechat diffusion has the nonlinear variation characteristics and the law which can not effectively described by signal prediction algorithm.Therefore~ this paper presents a Bass-BP diffusion model. Firstly, use the classical Bass model to preliminary forecast the Wechat＇s data, and then use the BP neural network to further non-linear approach the prediction results of Bass model. The results show that compared with Bass classic model and BP neural network, the Bass=BP combination model has better fitting effect and higher precision.

关 键 词：BASS模型 BP神经网络 微信扩散 Bass—BP组合模型 

分 类 号：O175[理学—数学] TP183[理学—基础数学]