Kristóf Németh, Dániel Hadházi
arXiv 24 May 2024 · Econometrics
arXiv:2405.15579 · PDF · DOI · OpenAlex · Extracted main text
Recent results in the literature indicate that artificial neural networks (ANNs) can outperform the dynamic factor model (DFM) in terms of the accuracy of GDP nowcasts. Compared to the DFM, the performance advantage of these highly flexible, nonlinear estimators is particularly evident in periods of recessions and structural breaks. From the perspective of policy-makers, however, nowcasts are the most useful when they are conveyed with uncertainty attached to them. While the DFM and other classical time series approaches analytically derive the predictive (conditional) distribution for GDP growth, ANNs can only produce point nowcasts based on their default training procedure (backpropagation). To fill this gap, first in the literature, we adapt two different deep learning algorithms that enable ANNs to generate density nowcasts for U.S. GDP growth: Bayes by Backprop and Monte Carlo dropout. The accuracy of point nowcasts, defined as the mean of the empirical predictive distribution, is evaluated relative to a naive constant growth model for GDP and a benchmark DFM specification. Using a 1D CNN as the underlying ANN architecture, both algorithms outperform those benchmarks during the evaluation period (2012:Q1 -- 2022:Q4). Furthermore, both algorithms are able to dynamically adjust the location (mean), scale (variance), and shape (skew) of the empirical predictive distribution. The results indicate that both Bayes by Backprop and Monte Carlo dropout can effectively augment the scope and functionality of ANNs, rendering them a fully compatible and competitive alternative for classical time series approaches.
appendix boundary found by appendix_command · 93% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Harvey, Andrew C (1990) Forecasting, structural time series models and the Kalman filter | 0.928 | 4 | 3 | 100% |
| 2 | Blundell, Charles, Cornebise, Julien, Kavukcuoglu, Koray, Wierstra,… (2015) Weight uncertainty in neural network | 0.811 | 4 | 2 | 100% |
| 3 | Durbin, James, Koopman, Siem Jan (2012) Time series analysis by state space methods | 0.737 | 3 | 2 | 100% |
| 4 | Gal, Yarin, Ghahramani, Zoubin (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning | 0.737 | 3 | 2 | 100% |
| 5 | Hopp, Daniel (2021) Economic nowcasting with long short-term memory artificial neural networks (LSTM) | 0.737 | 3 | 2 | 100% |
| 6 | Labonne, Paul (2020) Capturing GDP nowcast uncertainty in real time | 0.737 | 3 | 2 | 100% |
| 7 | Loermann, Julius, Maas, Benedikt (2019) Nowcasting US GDP with artificial neural networks | 0.737 | 3 | 2 | 100% |
| 8 | Mariano, Roberto S, Murasawa, Yasutomo (2003) A new coincident index of business cycles based on monthly and quarterly series | 0.737 | 3 | 2 | 100% |
| 9 | Giannone, Domenico, Reichlin, Lucrezia, Small, David (2008) Nowcasting: The real-time informational content of macroeconomic data | 0.585 | 3 | 1 | 100% |
| 10 | McCracken, Michael W, Ng, Serena (2016) FRED-MD: A monthly database for macroeconomic research | 0.511 | 2 | 2 | 50% |
Showing the top 10 of 44 scored citations.