Home

Economic Recession Prediction Using Deep Neural Network

Year
2022
Secondary
https://storage.googleapis.com/public-quant/integrate/papers/Economic%20Recession%20Prediction%20Using%20Deep%20Neural%20Network.pdf
Download
https://mega.co.nz/#!LXoURA7C!iUOktIBCsoWdeVwxaC-ghVnXOewgKrn7U6iVUucABf8
Abstract
1. Zihao Wang 1. is a student in the Michtom School of Computer Science at Brandeis University in Waltham, MA. (tonywang1997{at}brandeis.edu) 2. Kun Li 1. is a student in the Michtom School of Computer Science at Brandeis University in Waltham, MA. (kunli{at}brandeis.edu) 3. Steve Q. Xia 1. is a senior managing director at Guardian Life in New York, NY. (stevexia{at}glic.com) 4. Hongfu Liu 1. is an assistant professor in the Michtom School of Computer Science at Brandeis University in Waltham, MA. (hongfuliu{at}brandeis.edu) We investigate the effectiveness of different machine learning methodologies in predicting economic cycles. We identify the deep learning methodology of BiLSTM with autoencoder as the most accurate model to forecast the beginning and end of economic recessions in the United States. We adopt commonly available macro and market-condition features to compare the ability of different machine learning models to generate good predictions both in-sample and out-of-sample. The proposed model is flexible and dynamic when both predictive variables and model coefficients vary over time. It provided good out-of-sample predictions for the past two recessions and early warning about the COVID-19 recession.
Author
Zihao Wang and Kun Li and Steve Q. Xia and Hongfu Liu
View
https://sci-hub.st/10.3905/jfds.2022.1.097
Journal
https://arxiv.org/abs/2107.10980
Published
2022/06/20
Retrieved
6/21/2022, 1:39:33 AM
DOI
10.3905/jfds.2022.1.097
TOP