Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Inside the black box: Neural network-based real-time prediction of US recessions (2310.17571v3)

Published 26 Oct 2023 in econ.EM and stat.ML

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Asymmetric business cycles: Theory and time-series evidence. Journal of Monetary Economics 40(3), 501–533.
  2. Adaptive control processes: a guided tour. Princeton University Press.
  3. Evaluating the classification of economic activity into recessions and expansions. American Economic Journal: Macroeconomics 3(2), 246–277.
  4. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, 281–305.
  5. Credit growth, the yield curve and financial crisis prediction: evidence from a machine learning approach. Working paper no. 848, Bank of England 76, 417–427.
  6. Large-scale machine learning with stochastic gradient descent, in: Proceedings of COMPSTAT’2010, Springer-Verlag Berlin Heidelberg.
  7. A comparison of the real-time performance of business cycle dating methods. Journal of Business and Economic Statistics 26(1), 42–49.
  8. Forecasting recessions using the yield curve. Journal of Forecasting 24(2), 77–103.
  9. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 1724–1734.
  10. The relationship between precision-recall and roc curves. In Proceedings of the 23rd international conference on Machine learning , 233–240.
  11. Multicollinearity: a tale of two nonparametric regressions. Selecting models from data: artificial intelligence and statistics IV , 293–302.
  12. The yield curve as a recession leading indicator. an application for gradient boosting and random forest. arXiv: 2203.06648.
  13. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12, 2121–2159.
  14. Strengthening the case for the yield curve as a predictor of u.s. recessions. Federal Reserve Bank of St. Louis Review 79, 41–51.
  15. Regime-dependent recession forecasts and the 2001 recession. Federal Reserve Bank of St. Louis Review 84(6), 29–36.
  16. The yield curve as a predictor of u.s. recessions, current issues in economics and finance. Federel Reserve Bank of New York Research Paper Series 2(7), 1–6.
  17. Predicting u.s. recessions: Financial variables as leading indicators. The Review of Economics and Statistics 80(1), 45–61.
  18. Predicting recession probabilities with financial variables over multiple horizons. Working paper series 1255, European Central Bank.
  19. Forecasting us recessions with a large set of predictors. Journal of Forecasting 35(6), 477–492.
  20. Escaping from saddle points - online stochastic gradient for tensor decomposition. JMLR: Workshop and Conference Proceedings 40, 1–46.
  21. Long short-term memory. Neural Computation 9(8), 1735–1780.
  22. Ridge regression: Applications to nonorthogonal problems. Technometircs 12(1), 69–82.
  23. Toward robust early-warning models: a horse race, ensembles and model uncertainty. Journal of Quantitative Finance 17(12), 1933–1963.
  24. Multilayer feedforward networks are universal approximaters. Neural Networks 2, 359–366.
  25. Multivariate nonlinear forecasting: Using financial information to forecast the real sector. Macroeconomic Dynamics 2, 369–382.
  26. Adam: a method for stochastic optimization. arXiv: 1412.6980v9.
  27. Nn-svg: Publication-ready neural network architecture schematics,. ournal of Open Source Software 4(33), 747.
  28. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30.
  29. Artificial neural networks for some macroeconomic series: a first report. Econometric Reviews 13, 105–122.
  30. Statistical indicators of cyclical revivals. NBER Chapters: Business Cycle Indicators (1), 162–183.
  31. Interpretable machine learning: A guide for making black box models explainable 2ed. http://christophm.github.io/interpretable-ml-book/.
  32. The asymmetric business cycle. Review of Economics and Statistics 94(1), 208–221.
  33. Econometric versus ann models in forecasting inflation. Journal of Forecasting 19(3), 201–217.
  34. Viewpoint: boosting recessions. Canadian Journal of Economics 47, 1–34.
  35. A bivariate autoregressive probit model: Business cycle linkages and transmission of recession probabilities. Macroeconomic Dynamics 18(4), 838–862.
  36. Neural networks, the treasury yield curve, and recession forecasting. The Journal of Financial Data Science 3(2), 149–175.
  37. Predicting us recessions with leading indicators via neural network models. International Journal of Forecasting 17, 383–401.
  38. A value for n-person games. Contributions to the Theory of Games II AM-28, 307–317.
  39. Learning important features through propagating activation differences. International conference on machine learning PMLR, 3145–3153.
  40. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 1929–1958.
  41. Forecasting with a real-time data set for macroeconomists. Journal of Macroeconomics 24(4), 507–531.
  42. Missforest: Non-parametric missing value imputation for mixed-type data. Bioinformatics 28(1), 112–118.
  43. A comparison of linear and nonlinear univariate models for forecasting macroeconomic time series. NBER Working paper no. 6607.
  44. A model selection approach to real-time macroeconomic forecasting using linear models and artificial neural networks. The Review of Economics and Statistics 79, 540–550.
  45. Classification assessment methods. Applied Computing and Informatics 17(1), 168–192.
  46. Some advances in non-linear and adaptive modelling in time-series. Journal of Forecasting 13, 109–131.
  47. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B, 267–288.
  48. Rmsprop: divide the gradient by a running average of its recent magnitude. Neural Networks for Machine Learning 4, 26–31.
  49. Neural network forecasting of canadian gdp growth. International Journal of Forecasting 17, 57–69.
  50. Ssvm: a simple svm algorithm. Proceedings of the 2002 International Joint Conference on Neural Networks 3 IEEE, 2393–2398.
  51. Modeling and predicting u.s. recessions using machine learning techniques. International Journal of Forecasting 37, 647–671.
  52. Economic recession prediction using deep neural network. The Journal of Financial Data 4(3), 108–127.
  53. The yield curve and predicting recessions. FEDs Working Paper No. 2006‐07.
  54. An overview of overfitting and its solutions. Journal of Physics: Conference Series 1168, 022022.
  55. Forecasting with artificial neural networks: the state of the art. Internationial Journal of Forecasting 14, 35–62.
  56. A new optimization algorithm for non-stationary time series prediction based on recurrent neural networks. Future Generation Computer Systems 102, 738–745.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now