Search Results

You are looking at 1 - 10 of 20 items for :

  • "learning framework" x
Clear All
Karim Barhoumi, Seung Mo Choi, Tara Iyer, Jiakun Li, Franck Ouattara, Mr. Andrew J Tiffin, and Jiaxiong Yao
The COVID-19 crisis has had a tremendous economic impact for all countries. Yet, assessing the full impact of the crisis has been frequently hampered by the delayed publication of official GDP statistics in several emerging market and developing economies. This paper outlines a machine-learning framework that helps track economic activity in real time for these economies. As illustrative examples, the framework is applied to selected sub-Saharan African economies. The framework is able to provide timely information on economic activity more swiftly than official statistics.
Karim Barhoumi, Seung Mo Choi, Tara Iyer, Jiakun Li, Franck Ouattara, Mr. Andrew J Tiffin, and Jiaxiong Yao

more effective than traditional econometric methods . Machine learning models frequently employ techniques that are familiar to most economists; indeed, most machine-learning textbooks start with simple ordinary least squares (OLS) regression (see Appendix). However, the focus of machine-learning models is somewhat different from traditional econometric models. Instead of exploring issues of identification and causality, the primary focus of machine learning is on producing more precise out-of-sample predictions. To this end, a machine-learning framework will exploit

variable (κ) al- lows us to solve for the equilibrium dynamics following a two-stage solution method. In the first stage, we use the Bayesian learning framework to generate the agents’ sequence of posterior means determined by (6). In the second stage, we characterize the agents’ optimal plans as a recursive equilibrium by adopting Kreps’s Anticipated Utility (AU) approach to approximate dynamic opti- mization with Bayesian learning. The AU approach focuses on combining the sequences of posterior means obtained in the first stage with chained solutions from a set of

Mr. Jorge A Chan-Lau
We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes into time-invariant non-overlapping clusters, each of which could be identified with a different regime. The likelihood that a country may experience an econmic crisis could be set equal to its cluster crisis frequency. Moreover, unFEAR could serve as a first step towards developing cluster-specific crisis prediction models tailored to each crisis regime.
Tohid Atashbar and Rui Aruhan Shi
This study seeks to construct a basic reinforcement learning-based AI-macroeconomic simulator. We use a deep RL (DRL) approach (DDPG) in an RBC macroeconomic model. We set up two learning scenarios, one of which is deterministic without the technological shock and the other is stochastic. The objective of the deterministic environment is to compare the learning agent's behavior to a deterministic steady-state scenario. We demonstrate that in both deterministic and stochastic scenarios, the agent's choices are close to their optimal value. We also present cases of unstable learning behaviours. This AI-macro model may be enhanced in future research by adding additional variables or sectors to the model or by incorporating different DRL algorithms.
Man-Keung Tang and Mr. Xiangrong Yu
This paper studies the role of central bank communication of its economic assessment in shaping inflation dynamics. Imperfect information about the central bank's assessment - or the basis for monetary policy decisions - could complicate the private sector's learning about its policy response function. We show how clear central bank communication, which facilitates agents' understanding of policy reasoning, could bring about less volatile inflation and interest rate dynamics, and afford the authorities with greater policy flexibility. We then estimate a simple monetary model to fit the Mexican economy, and use the suggested paramters to illustrate the model's quantitative implications in scenarios where the timing, nature and persistence of shocks are uncertain.
Luiza Antoun de Almeida and Ms. Diva Singh
In recent years, we have observed an increase in low-income countries’ (LICs) access to international capital markets, especially after the Global Financial Crisis (GFC). This paper investigates what factors—country-specific macroeconomic fundamentals and/or external variables—have contributed to the surge in external bond issuance by these LICs, which we refer to in our paper as ‘frontier economies’. Using data on public and publicly guaranteed (PPG) external bond issuance, outstanding PPG bond stock, as well as sovereign spreads, we employ panel data analysis to examine factors related to the increase in issuance by these economies as well as the reduction in their spreads over time. Our empirical study shows that both country-specific fundamentals (such as public debt, current account balance, level of reserves, quality of institutions) and external variables (such as US growth and the VIX index) play a role in explaining the increased amount of issuance and the decline in spreads of frontier economies’ sovereign bonds. The impact of some of these variables on issuance appears to reflect a country’s need to issue bonds for external financing (‘the supply side’ of bond issuance), while others appear to correlate more through their impact on investors’ appetite for a country’s debt (‘the demand side’). In addition, the impact of country-specific variables can also be affected by external factors such as global risk appetite. Our analysis of key factors that have contributed to increased market access for frontier economies over the past decade provides important information to gauge the prospects for their continued market access, and for other LICs to join this group by tapping international markets for the first time.
Mr. Enrique G. Mendoza and Ms. Emine Boz
Uncertainty about the riskiness of new financial products was an important factor behind the U.S. credit crisis. We show that a boom-bust cycle in debt, asset prices and consumption characterizes the equilibrium dynamics of a model with a collateral constraint in which agents learn "by observation" the true riskiness of a new financial environment. Early realizations of states with high ability to leverage assets into debt turn agents optimistic about the persistence of a high-leverage regime. The model accounts for 69 percent of the household debt buildup and 53 percent of the rise in housing prices during 1997-2006, predicting a collapse in 2007.
Javier Bianchi, Ms. Emine Boz, and Mr. Enrique G. Mendoza
The interaction between credit frictions, financial innovation, and a switch from optimistic to pessimistic beliefs played a central role in the 2008 financial crisis. This paper develops a quantitative general equilibrium framework in which this interaction drives the financial amplification mechanism to study the effects of macro-prudential policy. Financial innovation enhances the ability of agents to collateralize assets into debt, but the riskiness of this new regime can only be learned over time. Beliefs about transition probabilities across states with high and low ability to borrow change as agents learn from observed realizations of financial conditions. At the same time, the collateral constraint introduces a pecuniary externality, because agents fail to internalize the effect of their borrowing decisions on asset prices. Quantitative analysis shows that the effectiveness of macro-prudential policy in this environment depends on the government's information set, the tightness of credit constraints and the pace at which optimism surges in the early stages of financial innovation. The policy is least effective when the government is as uninformed as private agents, credit constraints are tight, and optimism builds quickly.