nep-for New Economics Papers
on Forecasting
Issue of 2021‒03‒15
seven papers chosen by
Rob J Hyndman
Monash University

  1. A BVAR Model for Forecasting Ukrainian Inflation By Nadiia Shapovalenko; ;
  2. The narrative about the economy as a shadow forecast: an analysis using Banco de España quarterly reports By Nélida Díaz Sobrino; Corinna Ghirelli; Samuel Hurtado; Javier J. Pérez; Alberto Urtasun
  3. Forex exchange rate forecasting using deep recurrent neural networks By Dautel, Alexander Jakob; Härdle, Wolfgang Karl; Lessmann, Stefan; Seow, Hsin-Vonn
  4. Panel semiparametric quantile regression neural network for electricity consumption forecasting By Xingcai Zhou; Jiangyan Wang
  5. Forecasting Oil Price over 150 Years: The Role of Tail Risks By Afees A. Salisu; Rangan Gupta; Qiang Ji
  6. Thinking outside the container: A machine learning approach to forecasting trade flows By Stamer, Vincent
  7. Forecasting the Stability and Growth Pact compliance using Machine Learning. By Kéa Baret; Amélie Barbier-Gauchard; Théophilos Papadimitriou

  1. By: Nadiia Shapovalenko (National Bank of Ukraine); ;
    Abstract: In this paper, I examine the forecasting performance of a Bayesian Vector Autoregression (BVAR) model with steady-state prior and compare the accuracy of the forecasts against the forecasts of QPM model and official NBU forecasts over the period 2016q1–2020q1. My findings suggest that inflation forecasts produced by the BVAR model are more accurate than those of the QPM model two quarters ahead and are competitive for the longer horizon. For GDP growth, the forecasts of the BVAR outperform those of the QPM for the whole forecast horizon. For inflation they also outperform the official NBU forecasts over the monetary policy horizon, whereas the opposite is true for the forecasts of the GDP growth.
    Keywords: BVAR, forecast evaluation, inflation forecasting
    JEL: C30 C53 E37
    Date: 2021–03–05
  2. By: Nélida Díaz Sobrino (Universidad Nebrija); Corinna Ghirelli (Banco de España); Samuel Hurtado (Banco de España); Javier J. Pérez (Banco de España); Alberto Urtasun (Banco de España)
    Abstract: The aim of this paper is to construct a text-based indicator that reflects the sentiment of the Banco de España economic outlook reports. Our sentiment indicator mimics very closely the first release of the GDP growth rate, which is published after the publication of the reports, and the Banco de España quarterly forecasts of the GDP growth rate. This means that the qualitative narrative contained in the reports contains similar information to the one conveyed by the quantitative forecasts. In addition, the narrative complements the quantitative projections by discussing information which is not directly reflected in the point forecasts.
    Keywords: textual analysis, sentiment analysis, GDP growth rate, forecasting, central bank reports
    JEL: C53 C55 E37 E66 E58
    Date: 2020–12
  3. By: Dautel, Alexander Jakob; Härdle, Wolfgang Karl; Lessmann, Stefan; Seow, Hsin-Vonn
    Abstract: Deep learning has substantially advanced the state of the art in computer vision, natural language processing, and other fields. The paper examines the potential of deep learning for exchange rate forecasting. We systematically compare long short- term memory networks and gated recurrent units to traditional recurrent network architectures as well as feedforward networks in terms of their directional forecasting accuracy and the profitability of trading model predictions. Empirical results indicate the suitability of deep networks for exchange rate forecasting in general but also evidence the difficulty of implementing and tuning corresponding architectures. Especially with regard to trading profit, a simpler neural network may perform as well as if not better than a more complex deep neural network.
    Keywords: Deep learning,Financial time series forecasting,Recurrent neural networks,Foreign exchange rates
    JEL: C14 C22 C45
    Date: 2020
  4. By: Xingcai Zhou; Jiangyan Wang
    Abstract: China has made great achievements in electric power industry during the long-term deepening of reform and opening up. However, the complex regional economic, social and natural conditions, electricity resources are not evenly distributed, which accounts for the electricity deficiency in some regions of China. It is desirable to develop a robust electricity forecasting model. Motivated by which, we propose a Panel Semiparametric Quantile Regression Neural Network (PSQRNN) by utilizing the artificial neural network and semiparametric quantile regression. The PSQRNN can explore a potential linear and nonlinear relationships among the variables, interpret the unobserved provincial heterogeneity, and maintain the interpretability of parametric models simultaneously. And the PSQRNN is trained by combining the penalized quantile regression with LASSO, ridge regression and backpropagation algorithm. To evaluate the prediction accuracy, an empirical analysis is conducted to analyze the provincial electricity consumption from 1999 to 2018 in China based on three scenarios. From which, one finds that the PSQRNN model performs better for electricity consumption forecasting by considering the economic and climatic factors. Finally, the provincial electricity consumptions of the next $5$ years (2019-2023) in China are reported by forecasting.
    Date: 2021–02
  5. By: Afees A. Salisu (Centre for Econometric and Allied Research, University of Ibadan, Ibadan, Nigeria); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield, 0028, South Africa); Qiang Ji (Institutes of Science and Development, Chinese Academy of Sciences, Beijing, China; School of Public Policy and Management, University of Chinese Academy of Sciences, Beijing, China)
    Abstract: In this study, we examine the predictive value of tail risks for oil returns using the longest possible data available for the modern oil industry, i.e., 1859-2020. The Conditional Autoregressive Value at Risk (CAViaR) of Engle & Manganelli (2004) is employed to generate the tail risks for both 1% and 5% VaRs across four variants (Adaptive, Symmetric absolute value, Asymmetric slope and Indirect GARCH) of the CAViaR with the best variant obtained using the Dynamic Quantile test (DQ) test and %Hits. Overall, our proposed predictive model for oil returns that jointly accommodates tail risks associated with the oil market and US financial market improves the out-of-sample forecast accuracy of oil returns in contrast with a benchmark (random walk) model as well as a one-predictor model with own tail risk only. Our results have important implications for academicians, investors and policymakers.
    Keywords: Oil returns, Tail risks, Forecasting, Advanced equity markets
    JEL: C22 C53 G15 Q02
    Date: 2021–03
  6. By: Stamer, Vincent
    Abstract: Global container ship movements may reliably predict global trade flows. Aggregating both movements at sea and port call events produces a wealth of explanatory variables. The machine learning algorithm partial least squares can map these explanatory time series to unilateral imports and exports, as well as bilateral trade flows. Applying out-of-sample and time series methods on monthly trade data of 75 countries, this paper shows that the new shipping indicator outperforms benchmark models for the vast majority of countries. This holds true for predictions for the current and subsequent month even if one limits the analysis to data during the first half of the month. This makes the indicator available at least as early as other leading indicators.
    Keywords: Trade,Forecasting,Machine Learning,Container Shipping
    JEL: F17 C53
    Date: 2021
  7. By: Kéa Baret; Amélie Barbier-Gauchard; Théophilos Papadimitriou
    Abstract: Since the reinforcement of the Stability and Growth Pact (1996), the European Commission closely monitors public finance in the EU members. A failure to comply with the 3% limit rule on the public deficit by a country triggers an audit. In this paper, we present a Machine Learning based forecasting model for the compliance with the 3% limit rule. To do so, we use data spanning the period from 2006 to 2018 (a turbulent period including the Global Financial Crisis and the Sovereign Debt Crisis) for the 28 EU Member States. A set of eight features are identified as predictors from 141 variables through a feature selection procedure. The forecasting is performed using the Support Vector Machines (SVM). The proposed model reached 91.7% forecasting accuracy and outperformed the Logit model that we used as benchmark.
    Keywords: Fiscal Rules; Fiscal Compliance; Stability and Growth Pact; Machine learning.
    JEL: E62 H11 H60 H68
    Date: 2021

This nep-for issue is ©2021 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.