Search Results

You are looking at 1 - 10 of 49 items for :

  • "machine-learning algorithm" x
Clear All
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.
Marijn A. Bolhuis, Brett Rayner, and Mr. Donal McGettigan

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.

Benjamin Carton, Nan Hu, Mr. Joannes Mongardini, Kei Moriya, Aneta Radzikowski, and Mr. Benjamin L Hunt

exporting country), and the total amount of transactions during the month (in USD and in the currency of settlement). This paper uses the SWIFT data to improve the short-term forecast of international trade, together with Brent crude oil prices and the new export orders subcomponent of manufacturing Purchasing Managers’ Index (PMI) where available. Both linear regressions and machine-learning algorithms are used to extract the lead information content of SWIFT trade messages to improve the short-term forecast of world and national trade for 40 large economies. In doing

Benjamin Carton, Nan Hu, Mr. Joannes Mongardini, Kei Moriya, and Aneta Radzikowski
An essential element of the work of the Fund is to monitor and forecast international trade. This paper uses SWIFT messages on letters of credit, together with crude oil prices and new export orders of manufacturing Purchasing Managers’ Index (PMI), to improve the short-term forecast of international trade. A horse race between linear regressions and machine-learning algorithms for the world and 40 large economies shows that forecasts based on linear regressions often outperform those based on machine-learning algorithms, confirming the linear relationship between trade and its financing through letters of credit.
Jin-Kyu Jung, Manasa Patnam, Anna Ter-Martirosyan, and Mr. Vikram Haksar

true relationship between the variables in question ( Breiman, 2001 ). In such cases, therefore, the model can only be as good as its specification, regardless of what the data might suggest. In contrast, a different approach to statistical analysis in general and forecasting in particular is offered by machine learning algorithms, which make next to no assumption 2 about the underlying relationship between the variables at hand and instead rely on an algorithmic approach to finding a function which best represents the relationship between input and output data

Jin-Kyu Jung, Manasa Patnam, and Anna Ter-Martirosyan
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.
Joel Mokyr

the production of capital and consumer goods. The impact of computers on science has gone much beyond analyzing large-scale databases and standard statistical analysis: a new era of data science in which models are replaced by powerful mega-data-crunching machines has arrived. Powerful computers employ machine-learning algorithms to detect patterns that human minds could not have dreamed up. Rather than dealing with models, regularities and correlations are detected by powerful computers, even if they are “so twisty that the human brain can neither recall nor

Benjamin Carton, Nan Hu, Mr. Joannes Mongardini, Kei Moriya, and Aneta Radzikowski

I—International Trade Financing II—Charts and Linear Regression Results III—Machine-Learning Algorithms IV—Methodology for SWIFT Forecasts