GDP nowcasting with artificial neural networks: How much does long-term memory matter?

arXiv:2304.05805v3 Announce Type: replace-cross
Abstract: We apply artificial neural networks (ANNs) to nowcast quarterly GDP growth for the U.S. economy. Using the monthly FRED-MD database, we compare the nowcasting performance of five different ANN architectures: the multilayer perceptron (MLP), the one-dimensional convolutional neural network (1D CNN), the Elman recurrent neural network (RNN), the long short-term memory network (LSTM), and the gated recurrent unit (GRU). The empirical analysis presents results from two distinctively different evaluation periods. The first (2012:Q1 -- 2019:Q4) …

abstract ann anns apply architectures artificial artificial neural networks arxiv cnn convolutional neural network cs.ai cs.lg database econ.em economy five gdp growth long-term matter memory mlp network networks neural network neural networks nowcasting perceptron performance type