Browse

You are looking at 1 - 10 of 17 items for :

  • Books and Analytical Papers x
  • Intelligence (AI) & Semantics x
Clear All
Jin-Kyu Jung, Manasa Patnam, Anna Ter-Martirosyan, and Mr. Vikram Haksar

Forecasting macroeconomic variables is key to developing a view on a country's economic outlook. Most traditional forecasting models rely on fitting data to a pre-specified relationship between input and output variables, thereby assuming a specific functional and stochastic process underlying that process. We pursue a new approach to forecasting by employing a number of machine learning algorithms, a method that is data driven, and imposing limited restrictions on the nature of the true relationship between input and output variables. We apply the Elastic Net, SuperLearner, and Recurring Neural Network algorithms on macro data of seven, broadly representative, advanced and emerging economies and find that these algorithms can outperform traditional statistical models, thereby offering a relevant addition to the field of economic forecasting.

International Monetary Fund. Monetary and Capital Markets Department
This Basel Core Principles (BCP) for Effective Banking Supervision Detailed Assessment Report has been prepared in the context of the Financial Sector Assessment Program for the People’s Republic of China–Hong Kong Special Administrative Region (HKSAR). The Hong Kong Monetary Authority (HKMA) supervises a major international financial center which was affected, though not significantly so, by the financial crisis. The HKMA is maintaining its commitment to the international regulatory reform agenda and is an early adopter of many standards. Supervisory practices, standards, and approaches are well integrated, risk based and of very high quality. There is one area in relation to the overarching legislative framework and powers which warrants further attention. The HKMA enjoys clear de facto but not de jure operational independence. There are two important cross border dimensions for Hong Kong as an international financial center. One is related to HKSAR’s significant position as a host supervisor. The second is the increasing importance of Mainland China in the current portfolios and prospects of the locally incorporated institutions, and indeed in the choice of HKSAR as a platform for overseas institutions to establish relationships with Mainland China.
International Monetary Fund. Western Hemisphere Dept.
This Selected Issues explores ways for strengthening the current fiscal framework in Suriname and considers options for a new fiscal anchor. The paper provides an overview of mineral natural resources and their importance for the budget. It also lays out the current framework for fiscal planning and budget execution in Suriname and discusses the analytical underpinnings of modernizing it to make it more robust. The paper also presents estimates of long-term sustainability benchmarks based on the IMF’s policy toolkit for resource-rich developing countries. Suriname’s fiscal framework can be strengthened through a fiscal anchor rooted in the non-resource primary balance. Given the size of fiscal adjustment required to bring the non-resource primary balance in line with the long-term sustainability benchmark, a substantial transition period is needed to implement it. The IMF Staff’s adjustment scenario—designed to put public debt on the downward path—closes the current gap by less than half, implying that adjustment would need to continue beyond the 5-year horizon.
International Monetary Fund. Monetary and Capital Markets Department
Banking supervision and regulation by the Hong Kong Monetary Authority (HKMA) remain strong. This assessment confirms the 2014 Basel Core Principles assessment that the HKMA achieves a high level of compliance with the BCPs. The Basel III framework (and related guidance) and domestic and cross-border cooperation arrangements are firmly in place. The HKMA actively contributes to the development and implementation of relevant international standards. Updating their risk based supervisory approach helped the HKMA optimize supervisory resources. The HKMA’s highly experienced supervisory staff is a key driver to achieving one of the most sophisticated levels of supervision and regulation observed in Asia and beyond.
International Monetary Fund. Monetary and Capital Markets Department
he Hong Kong Special Administrative Region (HKSAR) is among the world’s major fintech hubs, well positioned to develop fintech initiatives from its traditional strengths in financial services. Key factors enabling the HKSAR to emerge as a fintech hub include its presence as an international financial center, its free-flowing talent and capital, a highly developed information and technology communication (ITC) infrastructure, and its most unique trait, a geographical and strategic advantage by proximity to the market in Mainland China.
Mr. S. Nuri Erbas and Chera L. Sayers
Knightian uncertainty (ambiguity) implies presence of uninsurable risks. Institutional quality may be a good indicator of Knightian uncertainty. This paper correlates non-life insurance penetration in 70 countries with income level, financial sector depth, country risk, a measure of cost of insurance, and the World Bank governance indexes. We find that institutional quality-transparency-uncertainty nexus is the dominant determinant of insurability across countries, surpassing the explanatory power of income level. Institutional quality, as it reflects on the level of uncertainty, is the deeper determinant of insurability. Insurability is lower when governance is weaker.
Mr. Andrew J Tiffin
Macroeconomic analysis in Lebanon presents a distinct challenge. For example, long delays in the publication of GDP data mean that our analysis often relies on proxy variables, and resembles an extended version of the “nowcasting” challenge familiar to many central banks. Addressing this problem—and mindful of the pitfalls of extracting information from a large number of correlated proxies—we explore some recent techniques from the machine learning literature. We focus on two popular techniques (Elastic Net regression and Random Forests) and provide an estimation procedure that is intuitively familiar and well suited to the challenging features of Lebanon’s data.
Marijn A. Bolhuis and Brett Rayner
We leverage insights from machine learning to optimize the tradeoff between bias and variance when estimating economic models using pooled datasets. Specifically, we develop a simple algorithm that estimates the similarity of economic structures across countries and selects the optimal pool of countries to maximize out-of-sample prediction accuracy of a model. We apply the new alogrithm by nowcasting output growth with a panel of 102 countries and are able to significantly improve forecast accuracy relative to alternative pools. The algortihm improves nowcast performance for advanced economies, as well as emerging market and developing economies, suggesting that machine learning techniques using pooled data could be an important macro tool for many countries.
Mr. Jorge A Chan-Lau and Ran Wang
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.