Inside the black box: Neural network-based real-time prediction of US recessions

arXiv:2310.17571v2 Announce Type: replace-cross
Abstract: A standard feedforward neural network (FFN) and two specific types of recurrent neural networks, long short-term memory (LSTM) and gated recurrent unit (GRU), are used for modeling US recessions in the period from 1967 to 2021. The estimated models are then employed to conduct real-time predictions of the Great Recession and the Covid-19 recession in the US. Their predictive performances are compared to those of the traditional linear models, the standard logit model and the …

abstract arxiv black box box econ.em gru inside long short-term memory lstm memory modeling network networks neural network neural networks prediction real-time recurrent neural networks standard stat.ml type types