Methods for Multi-Step Time Series Forecasting Neural Networks
Methods for Multi-Step Time Series Forecasting Neural Networks
复制标题
DOI：
10.4018/978-1-59140-176-6.ch012
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Doug M. Kline
中科院分区：
文献类型：
--
作者：
Doug M. Kline
在这项研究中，我们研究了两种方法的多步预测与神经网络：联合方法和独立的方法。本研究使用了M-3竞争季度数据系列的一个子集。这些方法相互比较，神经网络迭代方法，和一个基线去趋势去季节性天真的预测。三种方法的操作特性也进行了检查。我们的研究结果表明，对于较长的预测范围的联合方法表现更好，而短期的预测范围的独立方法表现更好。此外，独立方法的表现总是至少与基线朴素方法和神经网络迭代方法一样好或更好。
In this study, we examine two methods for Multi-Step forecasting with neural networks: the Joint Method and the Independent Method. A subset of the M-3 Competition quarterly data series is used for the study. The methods are compared to each other, to a neural network Iterative Method, and to a baseline de-trended de-seasonalized naïve forecast. The operating characteristics of the three methods are also examined. Our findings suggest that for longer forecast horizons the Joint Method performs better, while for short forecast horizons the Independent Method performs better. In addition, the Independent Method always performed at least as well as or better than the baseline naïve and neural network Iterative Methods.