Search Results

You are looking at 1 - 10 of 42 items for :

  • "ML technique" x
Clear All
Mr. Andrew J Tiffin

important. But for empirical economists, prediction by itself is not always enough. Questions concerning the effects of a particular policy, for example, present a fundamentally different problem; as the answers require us to estimate what would have happened in the absence of that policy stance. This is the central challenge of causal inference and has perhaps been a key reason why machine learning hasn’t made greater headway among economists. Predictions can be validated, and so lend themselves to ML techniques. Counterfactuals cannot, as we never get to see the

Mr. Andrew J Tiffin
Machine learning tools are well known for their success in prediction. But prediction is not causation, and causal discovery is at the core of most questions concerning economic policy. Recently, however, the literature has focused more on issues of causality. This paper gently introduces some leading work in this area, using a concrete example—assessing the impact of a hypothetical banking crisis on a country’s growth. By enabling consideration of a rich set of potential nonlinearities, and by allowing individually-tailored policy assessments, machine learning can provide an invaluable complement to the skill set of economists within the Fund and beyond.
International Monetary Fund. Strategy, Policy, & Review Department
The IMF’s Vulnerability Exercise (VE) is a cross-country exercise that identifies country-specific near-term macroeconomic risks. As a key element of the Fund’s broader risk architecture, the VE is a bottom-up, multi-sectoral approach to risk assessments for all IMF member countries. The VE modeling toolkit is regularly updated in response to global economic developments and the latest modeling innovations. The new generation of VE models presented here leverages machine-learning algorithms. The models can better capture interactions between different parts of the economy and non-linear relationships that are not well measured in ”normal times.” The performance of machine-learning-based models is evaluated against more conventional models in a horse-race format. The paper also presents direct, transparent methods for communicating model results.
International Monetary Fund. Strategy, Policy, & Review Department

models at the core of the VE. The paper also presents direct, transparent methods for communicating model results . ML techniques can sometimes appear to be a black box due to their complexity and infrequent (though rapidly growing) use in economics. Communication tools, developed to inform country teams about the model assessments, help take the last step from predicting to informing.

Jin-Kyu Jung, Manasa Patnam, and Anna Ter-Martirosyan

literature, that seeks to apply machine learning (ML) techniques to improve economic forecasting. Chakraborty and Joseph (2017) explore areas of application for machine learning models in the context of central banking and see a large number of possibilities where these could be employed for the work of policy-makers. Accordingly, some research has already taken upon applying these new tools for economic forecasting and to come up with an alternative way to compute economic forecasts. For instance, Biau and D’Elia (2010) employ a Random Forest algorithm to forecast

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.
International Monetary Fund. Legal Dept.

resourced for tracing and recovering instrumentalities and POC. The physical transportation of proceeds of drug trafficking such as cash and bearer negotiable instruments is a common ML technique in Colombia. Nondeclared and nondisclosed cross-border currency is routinely being seized and confiscated. Competent authorities pursue proceeds and instrumentalities through criminal confiscation and asset forfeiture mechanisms. Asset forfeiture is being applied effectively with important results. Asset forfeiture proceedings are autonomous and are independent from criminal

Majid Bazarbash

. FinTech credit 1 promises to offer loans at a higher speed and lower cost, and therefore grant loans to a larger fraction of the population, resulting in elevated financial inclusion 2 . Policymakers and economists have recognized FinTech’s potential to transform the financial system but have also raised concerns about the opaque nature of the way modern technology could create value and generate financial stability risks (The Bali FinTech Agenda (2018)). In particular, for assessing credit risk, FinTech companies rely heavily on machine learning (ML) techniques that