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

arXiv: https://arxiv.org/abs/2310.17571 · HTML: https://mlsanity.com/paper/2310.17571/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 58 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition](https://mlsanity.com/paper/1503.02101/) (2015)
- [Toward robust early-warning models: A horse race, ensembles and model uncertainty](https://mlsanity.com/paper/1501.04682/) (2015)
- [The Yield Curve as a Recession Leading Indicator. An Application for Gradient Boosting and Random Forest](https://mlsanity.com/paper/2203.06648/) (2022)

## Abstract (arXiv)

Long short-term memory (LSTM) and gated recurrent unit (GRU) are used to model US recessions from 1967 to 2021. Their predictive performances are compared to those of the traditional linear models. The out-of-sample performance suggests the application of LSTM and GRU in recession forecasting, especially for longer-term forecasts. The Shapley additive explanations (SHAP) method is applied to both groups of models. The SHAP-based different weight assignments imply the capability of these types of neural networks to capture the business cycle asymmetries and nonlinearities. The SHAP method delivers key recession indicators, such as the S&P 500 index for short-term forecasting up to 3 months and the term spread for longer-term forecasting up to 12 months. These findings are robust against other interpretation methods, such as the local interpretable model-agnostic explanations (LIME) and the marginal effects.