图书借阅流量行为季节预测模型

指出图书借阅流量行为预测是图书借阅行为学的一个重要研究方向,常规的借阅流量预测大多采用的是ARIMA时间序列模型,但普通时间序列预测模型的参数难以估计并且模型较难处理非平稳时间序列问题。基于时间序列的神经图书借阅模型研究是,根据图书借阅流量行为的季节性特点,提出季节型神经图书借阅模型。用模型对图书借阅流量行为的预测分析表明,该模型预测效果较好,结果合理,对进行图书借阅实时监控及图书借阅管理都具有一定的理论和实践价值。

Seasonal Model on Library Borrow Traffic Behavior

The prediction on library borrow traffic behavior is an important aspect of library borrow behaviorism research. Traditional models on library borrow traffic prediction are based on seasonal ARMA model, but it is diffficult in finding its parameters and in dealing with non-stationary time series. Based on the neural-network model of time series and the season of network traffic behavior, a seasonal model of neural-network is made by using artificial neural-network. At the same time, the idea of making data smoothly process before training is considered to improve the accuracy of prediction. The model was used in network traffic prediction of library borrow behaviorism. The calculation results indicate that the model is reasonable and its accuracy is better than seasonal ARMA model. It is valuable when being used in practices.