IMF Working Papers

An Algorithmic Crystal Ball: Forecasts-based on Machine Learning

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

November 1, 2018

Download PDF

Preview Citation

Format: Chicago

Jin-Kyu Jung, Manasa Patnam, and Anna Ter-Martirosyan. An Algorithmic Crystal Ball: Forecasts-based on Machine Learning, (USA: International Monetary Fund, 2018) accessed September 19, 2024

Disclaimer: IMF Working Papers describe research in progress by the author(s) and are published to elicit comments and to encourage debate. The views expressed in IMF Working Papers are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management.

Summary

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.

Subject: Artificial intelligence, Economic forecasting, Machine learning, Technology

Keywords: Artificial intelligence, Benchmark WEO performance, Data set, Decision tree algorithm, Forecast errors, Forecasts, Generation process, Global, Machine learning, Machine learning algorithm, Machine learning model, Random Forest algorithm, Random Forest algorithms to nowcast GDP growth, Real GDP, Test data, Time series, Time-series data, Training data, WEO benchmark, WEO forecast, WP

Publication Details

  • Pages:

    34

  • Volume:

    ---

  • DOI:

    ---

  • Issue:

    ---

  • Series:

    Working Paper No. 2018/230

  • Stock No:

    WPIEA2018230

  • ISBN:

    9781484380635

  • ISSN:

    1018-5941