期刊名称：Ovidius University Annals: Economic Sciences Series
电子版ISSN：2393-3127
出版年度：2013
卷号：13
期号：1
语种：English
出版社：Ovidius University Press
摘要：Prediction is very important in business planning. The ability to accurately predict the future is fundamental to many decision activities in sales,marketing,production,inventory control,personnel,and many other functional areas of business. Time series modeling approach is one of the major techniques widely used in practice. In general,there are two approaches to modeling and forecasting time series: linear approach and nonlinear approach. Linear models [2] were used for a long time and are still very useful,but linearity assumptions underlying these models may be too restrictive. A nonlinear model more flexible is Artificial Neural Networks (ANN),which have received attention recently [19]. The major advantage of neural networks is that they are data driven and does not require restrictive assumptions about the form of the basic model. In this paper emphasize the strengths and weaknesses of neural networks.
