Designing a Neural Network Model for Time Series Forecasting
Paola Andrea Sánchez, José Rafael García-González, Carlos Hernán Fajardo-Toro, Paloma Martínez Sánchez · Advances in business strategy and competitive advantage book series · 2019
Artificial neural networks are highly flexible and efficient tools in the approximation of time series patterns. In recent years, more than 5,000 studies oriented to the use of neural networks in time series forecasting have been evidenced in the extant literature. However, the methodology used for its specification and construction still involves a lot of trial and error or is inherited from econometric and statistical procedures that do not fit perfectly to the characteristics of the time series. This is especially true when they present non-linear behavior; moreover, it is not designed for working with neural networks. The objective of this chapter is to present a five-step guide for the specification, design, and validation of a neural network model for forecasting time series.