eprintid: 4081 rev_number: 10 eprint_status: archive userid: 69 dir: disk0/00/00/40/81 datestamp: 2021-03-17 10:04:23 lastmod: 2021-03-17 10:04:50 status_changed: 2021-03-17 10:04:23 type: monograph metadata_visibility: show creators_name: Longo, Luigi creators_name: Riccaboni, Massimo creators_name: Rungi, Armando creators_id: luigi.longo@imtlucca.it creators_id: massimo.riccaboni@imtlucca.it creators_id: armando.rungi@imtlucca.it title: A Neural Network Ensemble Approach for GDP Forecasting ispublished: pub subjects: HA subjects: HB divisions: EIC full_text_status: public monograph_type: imt_eic_working_paper keywords: Keywords: macroeconomic forecasting; machine learning; neural networks; dynamic factor model; Covid-19 crisis; Mixed frequency. JEL codes: C53, E37, 051 abstract: We propose an ensemble learning methodology to forecast the future US GDP growth release. Our approach combines a Recurrent Neural Network (RNN) with a Dynamic Factor model accounting for time-variation in mean with a General- ized Autoregressive Score (DFM-GAS). The analysis is based on a set of predictors encompassing a wide range of variables measured at different frequencies. The forecast exercise is aimed at evaluating the predictive ability of each model's com- ponent of the ensemble by considering variations in mean, potentially caused by recessions affecting the economy. Thus, we show how the combination of RNN and DFM-GAS improves forecasts of the US GDP growth rate in the aftermath of the 2008-09 global financial crisis. We find that a neural network ensemble markedly reduces the root mean squared error for the short-term forecast horizon. date: 2021-03 date_type: published number: 2 place_of_pub: Lucca pages: 35 institution: IMT School for Advanced Studies Lucca issn: 2279-6894 referencetext: Elena Andreou, Eric Ghysels, and Andros Kourtellos. Should macroeconomic forecasters use daily �nancial data and how? Journal of Business & Economic Statistics, 31(2): 240-251, 2013. Juan Antolin-Diaz, Thomas Drechsel, and Ivan Petrella. Advances in nowcasting economic activity: Secular trends, large shocks and new data. Large Shocks and New Data (August 8, 2020), 2020. Susan Athey. The impact of machine learning on economics. In The economics of arti�cial intelligence: An agenda, pages 507-547. University of Chicago Press, 2018. Susan Athey and Guido W Imbens. The state of applied econometrics: Causality and policy evaluation. Journal of Economic Perspectives, 31(2):3-32, 2017. Andrii Babii, Eric Ghysels, and Jonas Striaukas. Machine learning time series regressions with an application to nowcasting. arXiv preprint arXiv:2005.14057, 2020. Jushan Bai and Serena Ng. Determining the number of primitive shocks in factor models. Journal of Business & Economic Statistics, 25(1):52-60, 2007. Marta Ba�nbura, Domenico Giannone, Michele Modugno, and Lucrezia Reichlin. Nowcasting and the real-time data ow. In Handbook of economic forecasting, volume 2, pages 195-237. Elsevier, 2013. Matteo Barigozzi, Marc Hallin, Stefano Soccorsi, and Rainer von Sachs. Time-varying general dynamic factor models and the measurement of �nancial connectedness. Jour- nal of Econometrics, 2020. Dario Buono, Gian Luigi Mazzi, George Kapetanios, Massimiliano Marcellino, and Fotis Papailias. Big data types for macroeconomic nowcasting. Eurostat Review on National Accounts and Macroeconomic Indicators, 1(2017):93-145, 2017. Maximo Camacho, Gabriel Perez-Quiros, and Pilar Poncela. Markov-switching dynamic factor models in real time. 2012. Kai Carstensen, Markus Heinrich, Magnus Reif, and Maik H.Wolters. Predicting ordinary and severe recessions with a three-state markov-switching dynamic factor model: An application to the german business cycle. International Journal of Forecasting, 36(3): 829 - 850, 2020. ISSN 0169-2070. doi: https://doi.org/10.1016/j.ijforecast.2019.09.005. URL http://www.sciencedirect.com/science/article/pii/S0169207019302493. Kyunghyun Cho, Bart Van Merri�enboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014. Gregory C Chow. Tests of equality between sets of coeffcients in two linear regressions. Econometrica: Journal of the Econometric Society, pages 591-605, 1960. Jacopo Cimadomo, Domenico Giannone, Michele Lenza, Francesca Monti, and Andrej Sokol. Nowcasting with large bayesian vector autoregressions. 2021. Drew Creal, Siem Jan Koopman, and Andr�e Lucas. Generalized autoregressive score models with applications. Journal of Applied Econometrics, 28(5):777-795, 2013. Antonello D'Agostino, Luca Gambetti, and Domenico Giannone. Macroeconomic forecasting and structural change. Journal of applied econometrics, 28(1):82-101, 2013. Marco Del Negro and Chris Otrok. Dynamic factor models with time-varying parameters: measuring changes in international business cycles. FRB of New York Staff Report, (326), 2008. Francis X Diebold and Robert S Mariano. Comparing predictive accuracy. Journal of Business & economic statistics, 20(1):134-144, 2002. James Durbin and Siem Jan Koopman. Time series analysis by state space methods. Oxford university press, 2012. Claudia Foroni, Massimiliano Giuseppe Marcellino, and Dalibor Stevanovi�c. Forecasting the covid-19 recession and recovery: Lessons from the �nancial crisis. 2020. Aurelien Geron. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O'Reilly Media, 2019. Domenico Giannone, Lucrezia Reichlin, and Luca Sala. Monetary policy in real time. NBER macroeconomics annual, 19:161-200, 2004. Domenico Giannone, Lucrezia Reichlin, and David Small. Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4): 665-676, 2008a. Domenico Giannone, Lucrezia Reichlin, and David Small. Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4): 665-676, 2008b. Sepp Hochreiter. The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge- Based Systems, 6(02):107-116, 1998. Sepp Hochreiter and J�urgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997. A Joseph. Parametric inference with universal function approximators. 2019. Iebeling Kaastra and Milton Boyd. Designing a neural network for forecasting �nancial. Neurocomputing, 10:215-236, 1996. Dimitris Korobilis. Assessing the transmission of monetary policy using time-varying parameter dynamic factor models. Oxford Bulletin of Economics and Statistics, 75(2): 157-179, 2013. Alan Lapedes and Robert Farber. Nonlinear signal processing using neural networks: Prediction and system modelling. Technical report, 1987. Jim Lee. Measuring business cycle comovements in europe: Evidence from a dynamic factor model with time-varying parameters. Economics Letters, 115(3):438-440, 2012. Julius Loermann and Benedikt Maas. Nowcasting us gdp with arti�cial neural networks. 2019. Scott M Lundberg and Su-In Lee. A uni�ed approach to interpreting model predictions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30, pages 4765-4774. Curran Associates, Inc., 2017. URL https://proceedings. neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf. Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, and Qianli Liao. Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review. International Journal of Automation and Computing, 14(5):503-519, 2017. Adam Richardson, Thomas van Florenstein Mulder, and Tu�grul Vehbi. Nowcasting gdp using machine-learning algorithms: A real-time assessment. International Journal of Forecasting, 2020. Timo Terasvirta and Heather M Anderson. Characterizing nonlinearities in business cycles using smooth transition autoregressive models. Journal of applied econometrics, 7(S1):S119-S136, 1992. Andrew Ti�n. Seeing in the dark: a machine-learning approach to nowcasting in lebanon. 2016. Guoqiang Zhang, B Eddy Patuwo, and Michael Y Hu. Forecasting with arti�cial neural networks:: The state of the art. International journal of forecasting, 14(1):35-62, 1998. citation: Longo, Luigi and Riccaboni, Massimo and Rungi, Armando A Neural Network Ensemble Approach for GDP Forecasting. EIC working paper series #2/2021 ISSN 2279-6894. document_url: http://eprints.imtlucca.it/4081/1/WP_EIC_2_2021.pdf