?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.relation=http%3A%2F%2Feprints.imtlucca.it%2F4081%2F&rft.title=A+Neural+Network+Ensemble+Approach+for+GDP%0D%0AForecasting&rft.creator=Longo%2C+Luigi&rft.creator=Riccaboni%2C+Massimo&rft.creator=Rungi%2C+Armando&rft.subject=HA+Statistics&rft.subject=HB+Economic+Theory&rft.description=We+propose+an+ensemble+learning+methodology+to+forecast+the+future+US+GDP%0D%0Agrowth+release.+Our+approach+combines+a+Recurrent+Neural+Network+(RNN)+with%0D%0Aa+Dynamic+Factor+model+accounting+for+time-variation+in+mean+with+a+General-%0D%0Aized+Autoregressive+Score+(DFM-GAS).+The+analysis+is+based+on+a+set+of+predictors%0D%0Aencompassing+a+wide+range+of+variables+measured+at+different+frequencies.+The%0D%0Aforecast+exercise+is+aimed+at+evaluating+the+predictive+ability+of+each+model's+com-%0D%0Aponent+of+the+ensemble+by+considering+variations+in+mean%2C+potentially+caused+by%0D%0Arecessions+affecting+the+economy.+Thus%2C+we+show+how+the+combination+of+RNN+and%0D%0ADFM-GAS+improves+forecasts+of+the+US+GDP+growth+rate+in+the+aftermath+of+the%0D%0A2008-09+global+financial+crisis.+We+find+that+a+neural+network+ensemble+markedly%0D%0Areduces+the+root+mean+squared+error+for+the+short-term+forecast+horizon.&rft.date=2021-03&rft.type=Working+Paper&rft.type=NonPeerReviewed&rft.format=application%2Fpdf&rft.language=en&rft.rights=cc_by_nc&rft.identifier=http%3A%2F%2Feprints.imtlucca.it%2F4081%2F1%2FWP_EIC_2_2021.pdf&rft.identifier=++Longo%2C+Luigi+and+Riccaboni%2C+Massimo+and+Rungi%2C+Armando++A+Neural+Network+Ensemble+Approach+for+GDP+Forecasting.++EIC+working+paper+series++%232%2F2021+++++ISSN+2279-6894.++++++