Search Results
Journal Article
Machine Learning Approaches to Macroeconomic Forecasting
Forecasting macroeconomic conditions can be challenging, requiring forecasters to make many discretionary choices about the data and methods they use. Although forecasters underpin the choices they make about models and complexity with economic intuition and judgement, these assumptions can be flawed. {{p}} Machine learning approaches, on the other hand, automate as many of those choices as possible in a manner that is not subject to the discretion of the forecaster. Aaron Smalter Hall applies machine learning techniques to find an optimal forecasting model for the unemployment rate. His ...
Working Paper
Macroeconomic Indicator Forecasting with Deep Neural Networks
Economic policymaking relies upon accurate forecasts of economic conditions. Current methods for unconditional forecasting are dominated by inherently linear models {{p}} that exhibit model dependence and have high data demands. {{p}} We explore deep neural networks as an {{p}} opportunity to improve upon forecast accuracy with limited data and while remaining agnostic as to {{p}} functional form. We focus on predicting civilian unemployment using models based on four different neural network architectures. Each of these models outperforms bench- mark models at short time horizons. One model, ...
Journal Article
How Much Would China’s GDP Respond to a Slowdown in Housing Activity?
We analyze China's interindustry connections and show that China?s housing activity has become increasingly important to its GDP growth. Our results suggest that a 10 percent decline in final demand for real estate and housing-related construction would lead to a decline in total output of 2.2 percent, an effect more than two times larger than it would have been 10 years ago.
Working Paper
Recession forecasting using Bayesian classification
The authors demonstrated the use of a Nave Bayes model as a recession forecasting tool. The approach has a close connection to Markov-switching models and logistic regression but also important differences. In contrast to Markov-switching models, Nave Bayes treats National Bureau of Economic Research business cycle turning points as data rather than hidden states to be inferred by the model. Although Nave Bayes and logistic regression are asymptotically equivalent under certain distributional assumptions, the assumptions do not hold for business cycle data.
Working Paper
How Centralized is U.S. Metropolitan Employment?
Centralized employment remains a benchmark stylization of metropolitan land use.To address its empirical relevance, we delineate "central employment zones" (CEZs)- central business districts together with nearby concentrated employment|for 183 metropolitan areas in 2000. To do so, we first subjectively classify which census tracts in a training sample of metros belong to their metro's CEZ and then use a learning algorithm to construct a function that predicts our judgment. {{p}} Applying this prediction function to the full cross section of metros estimates the probability we would judge ...