IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2512.12499.html

Explainable Prediction of Economic Time Series Using IMFs and Neural Networks

Author

Listed:
  • Pablo Hidalgo
  • Julio E. Sandubete
  • Agust'in Garc'ia-Garc'ia

Abstract

This study investigates the contribution of Intrinsic Mode Functions (IMFs) derived from economic time series to the predictive performance of neural network models, specifically Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks. To enhance interpretability, DeepSHAP is applied, which estimates the marginal contribution of each IMF while keeping the rest of the series intact. Results show that the last IMFs, representing long-term trends, are generally the most influential according to DeepSHAP, whereas high-frequency IMFs contribute less and may even introduce noise, as evidenced by improved metrics upon their removal. Differences between MLP and LSTM highlight the effect of model architecture on feature relevance distribution, with LSTM allocating importance more evenly across IMFs.

Suggested Citation

  • Pablo Hidalgo & Julio E. Sandubete & Agust'in Garc'ia-Garc'ia, 2025. "Explainable Prediction of Economic Time Series Using IMFs and Neural Networks," Papers 2512.12499, arXiv.org.
    • Handle: RePEc:arx:papers:2512.12499
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2512.12499
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Indranil Ghosh & Esteban Alfaro-Cortés & Matías Gámez & Noelia García-Rubio, 2023. "COVID-19 Media Chatter and Macroeconomic Reflectors on Black Swan: A Spanish and Indian Stock Markets Comparison," Risks, MDPI, vol. 11(5), pages 1-27, May.
    2. Giuseppe Cascarino & Mirko Moscatelli & Fabio Parlapiano, 2022. "Explainable Artificial Intelligence: interpreting default forecasting models based on Machine Learning," Questioni di Economia e Finanza (Occasional Papers) 674, Bank of Italy, Economic Research and International Relations Area.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jorge Tejero, 2022. "Unwrapping black box models A case study in credit risk," Revista de Estabilidad Financiera, Banco de España, issue Otoño.
    2. Raffaele Marchi & Alessandro Moro, 2024. "Forecasting Fiscal Crises in Emerging Markets and Low-Income Countries with Machine Learning Models," Open Economies Review, Springer, vol. 35(1), pages 189-213, February.
    3. Jorge Tejero, 2022. "Unwrapping black box models A case study in credit risk," Financial Stability Review, Banco de España, issue Autumn.
    4. Ghosh, Indranil & Jana, Rabin K., 2024. "Clean energy stock price forecasting and response to macroeconomic variables: A novel framework using Facebook's Prophet, NeuralProphet and explainable AI," Technological Forecasting and Social Change, Elsevier, vol. 200(C).
    5. Citterio, Alberto, 2024. "Bank failure prediction models: Review and outlook," Socio-Economic Planning Sciences, Elsevier, vol. 92(C).
    6. Rosaria Cerrone, 2023. "Are Artificial Intelligence and Machine Learning Shaping a New Risk Management Approach?," International Business Research, Canadian Center of Science and Education, vol. 16(12), pages 1-82, December.
    7. Victor Chang & Qianwen Ariel Xu & Shola Habib Akinloye & Vladlena Benson & Karl Hall, 2025. "Prediction of bank credit worthiness through credit risk analysis: an explainable machine learning study," Annals of Operations Research, Springer, vol. 354(1), pages 247-271, November.
    8. Jorge Tejero, 2022. "Unwrapping black box models A case study in credit risk," Financial Stability Review, Banco de España, issue Autumn.
    9. Francesco Columba & Manuel Cugliari & Stefano Di Virgilio, 2026. "Credit Risk Assessment with Stacked Machine Learning," Mercati, infrastrutture, sistemi di pagamento (Markets, Infrastructures, Payment Systems) 73, Bank of Italy, Directorate General for Markets and Payment System.
    10. Antonietta di Salvatore & Mirko Moscatelli, 2024. "Improving survey information on household debt using granular credit databases," Questioni di Economia e Finanza (Occasional Papers) 839, Bank of Italy, Economic Research and International Relations Area.
    11. Andrés Alonso & José Manuel Carbó, 2022. "Accuracy of explanations of machine learning models for credit decisions," Working Papers 2222, Banco de España.
    12. Giuseppe Cascarino & Federica Ciocchetta & Stefano Pietrosanti & Ivan Quaglia, 2025. "Forecasting corporate default probabilities: a local logit approach for scenario analysis," Questioni di Economia e Finanza (Occasional Papers) 909, Bank of Italy, Economic Research and International Relations Area.

    More about this item

    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:arx:papers:2512.12499. 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.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.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.