IDEAS home Printed from https://ideas.repec.org/p/cpr/ceprdp/14024.html
   My bibliography  Save this paper

Will Artificial Intelligence Replace Computational Economists Any Time Soon?

Author

Listed:
  • Maliar, Serguei
  • Winant, Pablo

Abstract

Artificial intelligence (AI) has impressive applications in many fields (speech recognition, computer vision, etc.). This paper demonstrates that AI can be also used to analyze complex and high-dimensional dynamic economic models. We show how to convert three fundamental objects of economic dynamics -- lifetime reward, Bellman equation and Euler equation -- into objective functions suitable for deep learning (DL). We introduce all-in-one integration technique that makes the stochastic gradient unbiased for the constructed objective functions. We show how to use neural networks to deal with multicollinearity and perform model reduction in Krusell and Smith's (1998) model in which decision functions depend on thousands of state variables -- we literally feed distributions into neural networks! In our examples, the DL method was reliable, accurate and linearly scalable. Our ubiquitous Python code, built with Dolo and Google TensorFlow platforms, is designed to accommodate a variety of models and applications.

Suggested Citation

  • Maliar, Serguei & Winant, Pablo, 2019. "Will Artificial Intelligence Replace Computational Economists Any Time Soon?," CEPR Discussion Papers 14024, C.E.P.R. Discussion Papers.
    • Handle: RePEc:cpr:ceprdp:14024
    as

    Download full text from publisher

    File URL: https://cepr.org/publications/DP14024
    Download Restriction: CEPR Discussion Papers are free to download for our researchers, subscribers and members. If you fall into one of these categories but have trouble downloading our papers, please contact us at subscribers@cepr.org
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Chase Coleman & Spencer Lyon & Lilia Maliar & Serguei Maliar, 2021. "Matlab, Python, Julia: What to Choose in Economics?," Computational Economics, Springer;Society for Computational Economics, vol. 58(4), pages 1263-1288, December.
    2. Artem Kuriksha, 2021. "An Economy of Neural Networks: Learning from Heterogeneous Experiences," Papers 2110.11582, arXiv.org.
    3. Maliar, Lilia & Maliar, Serguei, 2022. "Deep learning classification: Modeling discrete labor choice," Journal of Economic Dynamics and Control, Elsevier, vol. 135(C).
    4. Jesús Fernández-Villaverde & Pablo A. Guerrón-Quintana, 2021. "Estimating DSGE Models: Recent Advances and Future Challenges," Annual Review of Economics, Annual Reviews, vol. 13(1), pages 229-252, August.
    5. Hui Chen & Antoine Didisheim & Simon Scheidegger, 2021. "Deep Structural Estimation: With an Application to Option Pricing," Papers 2102.09209, arXiv.org.
    6. Fernández-Villaverde, Jesús & Ebrahimi Kahou, Mahdi & Perla, Jesse & Sood, Arnav, 2021. "Exploiting Symmetry in High-Dimensional Dynamic Programming," CEPR Discussion Papers 16285, C.E.P.R. Discussion Papers.
    7. Jesús Fernández‐Villaverde & Samuel Hurtado & Galo Nuño, 2023. "Financial Frictions and the Wealth Distribution," Econometrica, Econometric Society, vol. 91(3), pages 869-901, May.
    8. Stähler, Nikolai, 2021. "The Impact of Aging and Automation on the Macroeconomy and Inequality," Journal of Macroeconomics, Elsevier, vol. 67(C).
    9. Harrison, Richard & Waldron, Matt, 2021. "Optimal policy with occasionally binding constraints: piecewise linear solution methods," Bank of England working papers 911, Bank of England.
    10. Lepetyuk, Vadym & Maliar, Lilia & Maliar, Serguei, 2020. "When the U.S. catches a cold, Canada sneezes: A lower-bound tale told by deep learning," Journal of Economic Dynamics and Control, Elsevier, vol. 117(C).
    11. Rui (Aruhan) Shi, 2021. "Learning from Zero: How to Make Consumption-Saving Decisions in a Stochastic Environment with an AI Algorithm," CESifo Working Paper Series 9255, CESifo.
    12. Rui & Shi, 2021. "Learning from zero: how to make consumption-saving decisions in a stochastic environment with an AI algorithm," Papers 2105.10099, arXiv.org, revised Feb 2022.

    More about this item

    Keywords

    Artificial intelligence; Machine learning; Deep learning; Neural network; Stochastic gradient; Dynamic models; Dynamic programming; Bellman equation; Euler equation; Value function;
    All these keywords.

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:cpr:ceprdp:14024. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: the person in charge (email available below). General contact details of provider: https://www.cepr.org .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.