English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Feedforward neural network (FFN) and two specific types of recurrent neuralnetwork, long short-term memory (LSTM) and gated recurrent unit (GRU), are usedfor modeling US recessions in the period from 1967 to 2021. The estimatedmodels are then employed to conduct real-time predictions of the GreatRecession and the Covid-19 recession in US. Their predictive performances arecompared to those of the traditional linear models, the logistic regressionmodel both with and without the ridge penalty. The out-of-sample performancesuggests the application of LSTM and GRU in the area of recession forecasting,especially for the long-term forecasting tasks. They outperform other types ofmodels across 5 forecasting horizons with respect to different types ofstatistical performance metrics. Shapley additive explanations (SHAP) method isapplied to the fitted GRUs across different forecasting horizons to gaininsight into the feature importance. The evaluation of predictor importancediffers between the GRU and ridge logistic regression models, as reflected inthe variable order determined by SHAP values. When considering the top 5predictors, key indicators such as the S\&P 500 index, real GDP, and privateresidential fixed investment consistently appear for short-term forecasts (upto 3 months). In contrast, for longer-term predictions (6 months or more), theterm spread and producer price index become more prominent. These findings aresupported by both local interpretable model-agnostic explanations (LIME) andmarginal effects.

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