Time series forecasting is a widely used statistical technique that use past data to predict future values of variables. Its applications span across various fields, including finance, economics, and marketing. Multivariate time series forecasting, which involves two or more variables, is more complex than univariate time series forecasting and to address this complexity, neural networks are commonly used. However, the selection of an appropriate forecasting method is contingent upon the specific characteristics of the data. This paper proposes a new methodology that addresses such an issue and applies it to climate forecasting. The use of time series forecasting in climate forecasting has the potential to enhance our understanding of climate change and its impacts on various aspects of human life.
Deep Learning and Metaheuristic for Multivariate Time-Series Forecasting
Zito F.;Cutello V.;Pavone M.
2023-01-01
Abstract
Time series forecasting is a widely used statistical technique that use past data to predict future values of variables. Its applications span across various fields, including finance, economics, and marketing. Multivariate time series forecasting, which involves two or more variables, is more complex than univariate time series forecasting and to address this complexity, neural networks are commonly used. However, the selection of an appropriate forecasting method is contingent upon the specific characteristics of the data. This paper proposes a new methodology that addresses such an issue and applies it to climate forecasting. The use of time series forecasting in climate forecasting has the potential to enhance our understanding of climate change and its impacts on various aspects of human life.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.