Affiliation:
1. University of California Los Angeles (UCLA)
Abstract
Abstract
Quantitative models are an important decision-making factor for policy makers and
investors. Predicting an economic recession with high accuracy and reliability would be
very beneficial for the society. This paper assesses machine learning technics to predict
economic recessions in United States using market sentiment and economic indicators
(seventy-five explanatory variables) from Jan 1986 – June 2022 on a monthly basis
frequency. In order to solve the issue of missing time-series data points, Autoregressive
Integrated Moving Average (ARIMA) method used to backcast explanatory variables.
Analysis started with reduction in high dimensional dataset to only most important
characters using Boruta algorithm, correlation matrix and solving multicollinearity issue.
Afterwards, built various cross-validated models, both probability regression methods
and machine learning technics, to predict recession binary outcome. The methods
considered are Probit, Logit, Elastic Net, Random Forest, Gradient Boosting, and Neural
Network. Lastly, discussed different model’s performance based on confusion matrix,
accuracy and F1score with potential reasons for their weakness and robustness.
Publisher
Research Square Platform LLC
Reference33 articles.
1. Can Machine Learning Catch The COVID-19 Recession?;Coulombe PG;National Institute Economic Review.,2021
2. Donoghue, E. (2009). Economic Dip, Decline or Downturn? An Examination of The Definition of Recession. Student Economic Review.
3. Yield Curve and Recession Forecasting in a Machine Learning Framework;Gogas P;Comput Econ,2014
4. ‘What is a recession?: A reprise’;Layton AP;Applied Economics,2003
5. Fifty years of classification and regression trees;Loh Wei-Yin;International Statistical Review,2014
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献