Forecasting daily electricity prices with monthly macroeconomic variables

Claudia Foroni, Francesco Ravazzolo, L. Rossini

Research output: Working paperProfessional

Abstract

We analyse the importance of macroeconomic information, such as industrial production index and oil price, for forecasting daily electricity prices in two of the main European markets, Germany and Italy. We do that by means of mixed-frequency models, introducing a Bayesian approach to reverse unrestricted MIDAS models (RU-MIDAS). We study the forecasting accuracy for different horizons (from 1 day ahead to 28 days ahead) and by considering different specifications of the models. We find gains around 20% at short horizons and around 10% at long horizons. Therefore, it turns out that the macroeconomic low frequency variables are more important for short horizons than for longer horizons. The benchmark is almost never included in the model confidence set.
Original languageEnglish
PublisherEuropean Central Bank
Publication statusPublished - 20 Mar 2019

Publication series

NameECB Working Paper Series

Fingerprint

Macroeconomic variables
Electricity price
Macroeconomics
Forecasting accuracy
Oil prices
Benchmark
Germany
Confidence set
Bayesian approach
Industrial production
Italy

Cite this

Foroni, C., Ravazzolo, F., & Rossini, L. (2019). Forecasting daily electricity prices with monthly macroeconomic variables. (2250 ed.) (ECB Working Paper Series). European Central Bank.
Foroni, Claudia ; Ravazzolo, Francesco ; Rossini, L. / Forecasting daily electricity prices with monthly macroeconomic variables. 2250. ed. European Central Bank, 2019. (ECB Working Paper Series).
@techreport{c76d5a3a2b104238b37d7a9c374f454c,
title = "Forecasting daily electricity prices with monthly macroeconomic variables",
abstract = "We analyse the importance of macroeconomic information, such as industrial production index and oil price, for forecasting daily electricity prices in two of the main European markets, Germany and Italy. We do that by means of mixed-frequency models, introducing a Bayesian approach to reverse unrestricted MIDAS models (RU-MIDAS). We study the forecasting accuracy for different horizons (from 1 day ahead to 28 days ahead) and by considering different specifications of the models. We find gains around 20{\%} at short horizons and around 10{\%} at long horizons. Therefore, it turns out that the macroeconomic low frequency variables are more important for short horizons than for longer horizons. The benchmark is almost never included in the model confidence set.",
author = "Claudia Foroni and Francesco Ravazzolo and L. Rossini",
year = "2019",
month = "3",
day = "20",
language = "English",
series = "ECB Working Paper Series",
publisher = "European Central Bank",
edition = "2250",
type = "WorkingPaper",
institution = "European Central Bank",

}

Foroni, C, Ravazzolo, F & Rossini, L 2019 'Forecasting daily electricity prices with monthly macroeconomic variables' ECB Working Paper Series, 2250 edn, European Central Bank.

Forecasting daily electricity prices with monthly macroeconomic variables. / Foroni, Claudia; Ravazzolo, Francesco; Rossini, L.

2250. ed. European Central Bank, 2019. (ECB Working Paper Series).

Research output: Working paperProfessional

TY - UNPB

T1 - Forecasting daily electricity prices with monthly macroeconomic variables

AU - Foroni, Claudia

AU - Ravazzolo, Francesco

AU - Rossini, L.

PY - 2019/3/20

Y1 - 2019/3/20

N2 - We analyse the importance of macroeconomic information, such as industrial production index and oil price, for forecasting daily electricity prices in two of the main European markets, Germany and Italy. We do that by means of mixed-frequency models, introducing a Bayesian approach to reverse unrestricted MIDAS models (RU-MIDAS). We study the forecasting accuracy for different horizons (from 1 day ahead to 28 days ahead) and by considering different specifications of the models. We find gains around 20% at short horizons and around 10% at long horizons. Therefore, it turns out that the macroeconomic low frequency variables are more important for short horizons than for longer horizons. The benchmark is almost never included in the model confidence set.

AB - We analyse the importance of macroeconomic information, such as industrial production index and oil price, for forecasting daily electricity prices in two of the main European markets, Germany and Italy. We do that by means of mixed-frequency models, introducing a Bayesian approach to reverse unrestricted MIDAS models (RU-MIDAS). We study the forecasting accuracy for different horizons (from 1 day ahead to 28 days ahead) and by considering different specifications of the models. We find gains around 20% at short horizons and around 10% at long horizons. Therefore, it turns out that the macroeconomic low frequency variables are more important for short horizons than for longer horizons. The benchmark is almost never included in the model confidence set.

M3 - Working paper

T3 - ECB Working Paper Series

BT - Forecasting daily electricity prices with monthly macroeconomic variables

PB - European Central Bank

ER -

Foroni C, Ravazzolo F, Rossini L. Forecasting daily electricity prices with monthly macroeconomic variables. 2250 ed. European Central Bank. 2019 Mar 20. (ECB Working Paper Series).