IDEAS home Printed from https://ideas.repec.org/a/eee/finlet/v86y2025ipbs1544612325016782.html

Detecting bubbles via deterioration in machine learning predictive accuracy

Author

Listed:
  • Minami, Koutaroh

Abstract

This study explores the potential of machine learning, Long Short-Term Memory (LSTM), to detect asset price bubbles by analyzing prediction errors. Using monthly data of the Nikkei225 Index, I evaluate the performance of the LSTM model in forecasting prices and compare it with the GSADF test. I find that LSTM’s prediction accuracy significantly deteriorates during periods associated with asset bubbles, suggesting the presence of structural changes. In particular, the LSTM approach in this paper captures both the emergence and collapse of Japan’s late 1980s bubble separately. In addition, it can also capture structural changes related to policy changes in Japan during the 2010s, which are not identified by the GSADF test. These findings suggest that machine learning can be used not only for identifying bubbles but also for evaluating policies.

Suggested Citation

  • Minami, Koutaroh, 2025. "Detecting bubbles via deterioration in machine learning predictive accuracy," Finance Research Letters, Elsevier, vol. 86(PB).
    • Handle: RePEc:eee:finlet:v:86:y:2025:i:pb:s1544612325016782
    DOI: 10.1016/j.frl.2025.108424
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1544612325016782
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.frl.2025.108424?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Daniele Bianchi & Matthias Büchner & Andrea Tamoni, 2021. "Bond Risk Premiums with Machine Learning [Quadratic term structure models: Theory and evidence]," The Review of Financial Studies, Society for Financial Studies, vol. 34(2), pages 1046-1089.
    2. Peter C. B. Phillips & Shuping Shi & Jun Yu, 2015. "Testing For Multiple Bubbles: Historical Episodes Of Exuberance And Collapse In The S&P 500," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 56(4), pages 1043-1078, November.
    3. Kai Li & Feng Mai & Rui Shen & Xinyan Yan, 2021. "Measuring Corporate Culture Using Machine Learning," NBER Chapters, in: Big Data: Long-Term Implications for Financial Markets and Firms, pages 3265-3315, National Bureau of Economic Research, Inc.
    4. Sima Siami-Namini & Akbar Siami Namin, 2018. "Forecasting Economics and Financial Time Series: ARIMA vs. LSTM," Papers 1803.06386, arXiv.org.
    5. Ze Shen & Qing Wan & David J. Leatham, 2021. "Bitcoin Return Volatility Forecasting: A Comparative Study between GARCH and RNN," JRFM, MDPI, vol. 14(7), pages 1-18, July.
    6. Peter C. B. Phillips & Yangru Wu & Jun Yu, 2011. "EXPLOSIVE BEHAVIOR IN THE 1990s NASDAQ: WHEN DID EXUBERANCE ESCALATE ASSET VALUES?," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 52(1), pages 201-226, February.
    7. Kai Li & Feng Mai & Rui Shen & Xinyan Yan, 2021. "Measuring Corporate Culture Using Machine Learning [Machine learning methods that economists should know about]," The Review of Financial Studies, Society for Financial Studies, vol. 34(7), pages 3265-3315.
    8. Peter C. B. Phillips & Shuping Shi & Jun Yu, 2015. "Testing For Multiple Bubbles: Historical Episodes Of Exuberance And Collapse In The S&P 500," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 56, pages 1043-1078, November.
    9. Shun Chen & Lei Ge, 2019. "Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction," Quantitative Finance, Taylor & Francis Journals, vol. 19(9), pages 1507-1515, September.
    10. Ghosh, Pushpendu & Neufeld, Ariel & Sahoo, Jajati Keshari, 2022. "Forecasting directional movements of stock prices for intraday trading using LSTM and random forests," Finance Research Letters, Elsevier, vol. 46(PA).
    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. MINAMI, Koutaroh, 2025. "Detecting Bubbles by Machine Learning Prediction," Working Paper Series G-1-30, Hitotsubashi University Center for Financial Research.
    2. Wang, Xiao-Qing & Wu, Tong & Zhong, Huaming & Su, Chi-Wei, 2023. "Bubble behaviors in nickel price: What roles do geopolitical risk and speculation play?," Resources Policy, Elsevier, vol. 83(C).
    3. Michalski, Lachlan & Low, Rand Kwong Yew, 2024. "Determinants of corporate credit ratings: Does ESG matter?," International Review of Financial Analysis, Elsevier, vol. 94(C).
    4. Francisco Blasques & Siem Jan Koopman & Gabriele Mingoli, 2023. "Observation-Driven filters for Time- Series with Stochastic Trends and Mixed Causal Non-Causal Dynamics," Tinbergen Institute Discussion Papers 23-065/III, Tinbergen Institute, revised 01 Mar 2024.
    5. Bielskis, Karolis & Lastauskas, Povilas, 2024. "The role of housing market and credit on household consumption dynamics: Evidence from the OECD countries," Journal of Economic Behavior & Organization, Elsevier, vol. 228(C).
    6. Horváth, Lajos & Li, Hemei & Liu, Zhenya, 2022. "How to identify the different phases of stock market bubbles statistically?," Finance Research Letters, Elsevier, vol. 46(PA).
    7. Adrian Fernández-Pérez & Marta Gómez-Puig & Simón Sosvilla-Rivero, 2025. "El Clasico of Housing: Bubbles in Madrid and Barcelona’s Real Estate Markets," Documentos de Trabajo del ICAE 2025-03, Universidad Complutense de Madrid, Facultad de Ciencias Económicas y Empresariales, Instituto Complutense de Análisis Económico.
    8. Wang, Xichen & Yan, Ji (Karena) & Yan, Cheng & Gozgor, Giray, 2021. "Emerging stock market exuberance and international short-term flows," Journal of International Financial Markets, Institutions and Money, Elsevier, vol. 75(C).
    9. Chen, Bin-xia & Sun, Yan-lin, 2024. "Risk characteristics and connectedness in cryptocurrency markets: New evidence from a non-linear framework," The North American Journal of Economics and Finance, Elsevier, vol. 69(PA).
    10. Janusz Sobieraj & Dominik Metelski, 2021. "Testing Housing Markets for Episodes of Exuberance: Evidence from Different Polish Cities," JRFM, MDPI, vol. 14(9), pages 1-29, September.
    11. Victor Duarte & Diogo Duarte & Dejanir H. Silva, 2024. "Machine Learning for Continuous-Time Finance," CESifo Working Paper Series 10909, CESifo.
    12. Assaf, Ata & Demir, Ender & Ersan, Oguz, 2024. "Detecting and date-stamping bubbles in fan tokens," International Review of Economics & Finance, Elsevier, vol. 92(C), pages 98-113.
    13. Cervera, Ignacio & Figuerola-Ferretti, Isabel, 2024. "Credit risk and bubble behavior of credit default swaps in the corporate energy sector," International Review of Economics & Finance, Elsevier, vol. 89(PA), pages 702-731.
    14. Wang, Zuyi & Kim, Man-Keun, 2022. "Price bubbles in oil & gas markets and their transfer," Resources Policy, Elsevier, vol. 79(C).
    15. Francesco Giancaterini & Alain Hecq & Joann Jasiak & Aryan Manafi Neyazi, 2025. "Bubble Detection with Application to Green Bubbles: A Noncausal Approach," Papers 2505.14911, arXiv.org, revised Apr 2026.
    16. Abraham Atsiwo, 2025. "A three-step machine learning approach to predict market bubbles with financial news," Papers 2510.16636, arXiv.org.
    17. Caravello, Tomas E. & Psaradakis, Zacharias & Sola, Martin, 2023. "Rational bubbles: Too many to be true?," Journal of Economic Dynamics and Control, Elsevier, vol. 151(C).
    18. Tsai, I-Chun & Lin, Che-Chun, 2022. "A re-examination of housing bubbles: Evidence from European countries," Economic Systems, Elsevier, vol. 46(2).
    19. Cincinelli, Peter & Pellini, Elisabetta, 2025. "The role of geopolitical and climate risk in driving uncertainty in European electricity markets," Energy Economics, Elsevier, vol. 144(C).
    20. Kong, Xiaolin & Ma, Chaoqun & Ren, Yi-Shuai & Baltas, Konstantinos & Narayan, Seema, 2024. "A comparative analysis of the price explosiveness in Bitcoin and forked coins," Finance Research Letters, Elsevier, vol. 61(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • G10 - Financial Economics - - General Financial Markets - - - General (includes Measurement and Data)
    • G17 - Financial Economics - - General Financial Markets - - - Financial Forecasting and Simulation

    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:eee:finlet:v:86:y:2025:i:pb:s1544612325016782. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/frl .

    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.