|
on Forecasting |
| By: | Matteo Mogliani; Florens Odendahl |
| Abstract: | The popular choice of using a $direct$ forecasting scheme implies that the individual predictions do not contain information on cross-horizon dependence. However, this dependence is needed if the forecaster has to construct, based on $direct$ density forecasts, predictive objects that are functions of several horizons ($e.g.$ when constructing annual-average growth rates from quarter-on-quarter growth rates). To address this issue we propose to use copulas to combine the individual $h$-step-ahead predictive distributions into a joint predictive distribution. Our method is particularly appealing to practitioners for whom changing the $direct$ forecasting specification is too costly. In a Monte Carlo study, we demonstrate that our approach leads to a better approximation of the true density than an approach that ignores the potential dependence. We show the superior performance of our method in several empirical examples, where we construct (i) quarterly forecasts using month-on-month $direct$ forecasts, (ii) annual-average forecasts using monthly year-on-year $direct$ forecasts, and (iii) annual-average forecasts using quarter-on-quarter $direct$ forecasts. |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2412.06092 |
| By: | Christiane Baumeister; Florian Huber; Thomas K. Lee; Francesco Ravazzolo |
| Abstract: | This paper provides a comprehensive analysis of the forecastability of the real price of natural gas in the United States at the monthly frequency considering a universe of models that differ in their complexity and economic content. Our key finding is that considerable reductions in mean-squared prediction error relative to a random walk benchmark can be achieved in real time for forecast horizons of up to two years. A particularly promising model is a six-variable Bayesian vector autoregressive model that includes the fundamental determinants of the supply and demand for natural gas. To capture real-time data constraints of these and other predictor variables, we assemble a rich database of historical vintages from multiple sources. We also compare our model-based forecasts to readily available model-free forecasts provided by experts and futures markets. Given that no single forecasting method dominates all others, we explore the usefulness of pooling forecasts and find that combining forecasts from individual models selected in real time based on their most recent performance delivers the most accurate forecasts. |
| JEL: | C11 C32 C52 Q41 Q47 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33156 |
| By: | Pål Boug; Håvard Hungnes (Statistics Norway); Takamitsu Kurita |
| Abstract: | This paper examines the forecast accuracy of cointegrated vector autoregressive models when confronted with extreme observations at the end of the sample period. It focuses on comparing two outlier correction methods, additive outliers and innovational outliers, within a forecasting framework for macroeconomic variables. Drawing on data from the COVID-19 pandemic, the study empirically demonstrates that cointegrated vector autoregressive models incorporating additive outlier corrections outperform both those with innovational outlier corrections and no outlier corrections in forecasting post-pandemic household consumption. Theoretical analysis and Monte Carlo simulations further support these findings, showing that additive outlier adjustments are particularly effective when macroeconomic variables rapidly return to their initial trajectories following short-lived extreme observations, as in the case of pandemics. These results carry important implications for macroeconomic forecasting, emphasising the usefulness of additive outlier corrections in enhancing forecasts after periods of transient extreme observations. |
| Keywords: | Extreme observations; additive outliers; innovational outliers; cointegrated vector autoregressive models; forecasting |
| JEL: | C32 C53 E21 E27 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:ssb:dispap:1018 |
| By: | Stéphane Goutte (PSB - Paris School of Business - HESAM - HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université, SOURCE - SOUtenabilité et RésilienCE - UVSQ - Université de Versailles Saint-Quentin-en-Yvelines - IRD [Ile-de-France] - Institut de Recherche pour le Développement); Klemens Klotzner; Hoang Viet Le (SOURCE - SOUtenabilité et RésilienCE - UVSQ - Université de Versailles Saint-Quentin-en-Yvelines - IRD [Ile-de-France] - Institut de Recherche pour le Développement); Hans Jörg von Mettenheim (IPAG Business School) |
| Abstract: | In this paper, we address the refinement of solar energy forecasting within a 2-day window by integrating weather forecast data and strategically employing entity embedding, with a specific focus on the Multilayer Perceptron (MLP) algorithm. Through the analysis of two years of hourly solar energy production data from 16 power plants in Northern Italy (2020-2021), our research underscores the substantial impact of weather variables on solar energy production. Notably, we explore the augmentation of forecasting models by incorporating entity embedding, with a particular emphasis on embedding techniques for both general weather descriptors and individual power plants. By highlighting the nuanced integration of entity embedding within the MLP algorithm, our study reveals a significant enhancement in forecasting accuracy compared to popular machine learning algorithms like XGBoost and LGBM, showcasing the potential of this approach for more precise solar energy forecasts. |
| Keywords: | Entity embedding, Machine learning, Neural networks, Solar energy, Time series forecasting |
| Date: | 2024–09–06 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04779953 |