In this paper, we propose a machine learning approach for forecasting hierarchical time series. When dealing with hierarchical time series, apart from generating accurate forecasts, one needs to select a suitable method for producing reconciled forecasts. Forecast reconciliation is the process of adjusting forecasts to make them coherent across the hierarchy. In literature, coherence is often enforced by using a post-processing technique on the base forecasts produced by suitable time series forecasting methods. On the contrary, our idea is to use a deep neural network to directly produce accurate and reconciled forecasts. We exploit the ability of a deep neural network to extract information capturing the structure of the hierarchy. We impose the reconciliation at training time by minimizing a customized loss function. In many practical applications, besides time series data, hierarchical time series include explanatory variables that are beneficial for increasing the forecasting accuracy. Exploiting this further information, our approach links the relationship between time series features extracted at any level of the hierarchy and the explanatory variables into an end-to-end neural network providing accurate and reconciled point forecasts. The effectiveness of the approach is validated on three real-world datasets, where our method outperforms state-of-the-art competitors in hierarchical forecasting.

Mancuso, P., Piccialli, V., Sudoso, A. (2021). A machine learning approach for forecasting hierarchical time series. EXPERT SYSTEMS WITH APPLICATIONS, 182, 115102 [10.1016/j.eswa.2021.115102].

A machine learning approach for forecasting hierarchical time series

Mancuso, P;Piccialli, V;
2021

Abstract

In this paper, we propose a machine learning approach for forecasting hierarchical time series. When dealing with hierarchical time series, apart from generating accurate forecasts, one needs to select a suitable method for producing reconciled forecasts. Forecast reconciliation is the process of adjusting forecasts to make them coherent across the hierarchy. In literature, coherence is often enforced by using a post-processing technique on the base forecasts produced by suitable time series forecasting methods. On the contrary, our idea is to use a deep neural network to directly produce accurate and reconciled forecasts. We exploit the ability of a deep neural network to extract information capturing the structure of the hierarchy. We impose the reconciliation at training time by minimizing a customized loss function. In many practical applications, besides time series data, hierarchical time series include explanatory variables that are beneficial for increasing the forecasting accuracy. Exploiting this further information, our approach links the relationship between time series features extracted at any level of the hierarchy and the explanatory variables into an end-to-end neural network providing accurate and reconciled point forecasts. The effectiveness of the approach is validated on three real-world datasets, where our method outperforms state-of-the-art competitors in hierarchical forecasting.
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore ING-IND/35
English
Hierarchical time series
Forecast
Machine learning
Deep neural network
Mancuso, P., Piccialli, V., Sudoso, A. (2021). A machine learning approach for forecasting hierarchical time series. EXPERT SYSTEMS WITH APPLICATIONS, 182, 115102 [10.1016/j.eswa.2021.115102].
Mancuso, P; Piccialli, V; Sudoso, A
Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
A machine learning approach for forecasting hierarchical time series.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 752.43 kB
Formato Adobe PDF
752.43 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/294009
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 3
social impact