IDEAS home Printed from https://ideas.repec.org/p/pav/demwpp/demwp0140.html
   My bibliography  Save this paper

Deep Learning Bank Distress from News and Numerical Financial Data

Author

Listed:
  • Paola Cerchiello

    (Department of Economics and Management, University of Pavia)

  • Giancarlo Nicola

    (Department of Economics and Management, University of Pavia)

  • Samuel Rönnqvist

    (Turku Centre for Computer Science - TUCS, Åbo Akademi University)

  • Peter Sarlin

    (Hanken School of Economics, RiskLab Finland)

Abstract

In this paper we focus our attention on the exploitation of the information contained in financial news to enhance the performance of a classifier of bank distress. Such information should be analyzed and inserted into the predictive model in the most efficient way and this task deals with all the issues related to text analysis and specifically analysis of news media. Among the different models proposed for such purpose, we investigate one of the possible deep learning approaches, based on a doc2vec representation of the textual data, a kind of neural network able to map the sequential and symbolic text input onto a reduced latent semantic space. Afterwards, a second supervised neural network is trained combining news data with standard financial figures to classify banks whether in distressed or tranquil states, based on a small set of known distress events. Then the final aim is not only the improvement of the predictive performance of the classifier but also to assess the importance of news data in the classification process. Does news data really bring more useful information not contained in standard financial variables? Our results seem to confirm such hypothesis.

Suggested Citation

  • Paola Cerchiello & Giancarlo Nicola & Samuel Rönnqvist & Peter Sarlin, 2017. "Deep Learning Bank Distress from News and Numerical Financial Data," DEM Working Papers Series 140, University of Pavia, Department of Economics and Management.
    • Handle: RePEc:pav:demwpp:demwp0140
    as

    Download full text from publisher

    File URL: http://dem-web.unipv.it/web/docs/dipeco/quad/ps/RePEc/pav/demwpp/DEMWP0140.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Betz, Frank & Oprică, Silviu & Peltonen, Tuomas A. & Sarlin, Peter, 2014. "Predicting distress in European banks," Journal of Banking & Finance, Elsevier, vol. 45(C), pages 225-241.
    2. Sarlin, Peter, 2013. "On policymakers’ loss functions and the evaluation of early warning systems," Economics Letters, Elsevier, vol. 119(1), pages 1-7.
    3. David Bholat & Stephen Hans & Pedro Santos & Cheryl Schonhardt-Bailey, 2015. "Text mining for central banks," Handbooks, Centre for Central Banking Studies, Bank of England, number 33, April.
    4. Pekka Malo & Ankur Sinha & Pekka Korhonen & Jyrki Wallenius & Pyry Takala, 2014. "Good debt or bad debt: Detecting semantic orientations in economic texts," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 65(4), pages 782-796, April.
    Full references (including those not matched with items on IDEAS)

    Citations

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


    Cited by:

    1. Ahmet Murat Ozbayoglu & Mehmet Ugur Gudelek & Omer Berat Sezer, 2020. "Deep Learning for Financial Applications : A Survey," Papers 2002.05786, arXiv.org.
    2. Yi Cao & Xiaoquan Liu & Jia Zhai & Shan Hua, 2022. "A two‐stage Bayesian network model for corporate bankruptcy prediction," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 27(1), pages 455-472, January.
    3. Mary Chen & Matthew DeHaven & Isabel Kitschelt & Seung Jung Lee & Martin J. Sicilian, 2023. "Identifying Financial Crises Using Machine Learning on Textual Data," JRFM, MDPI, vol. 16(3), pages 1-28, March.
    4. Buckmann, Marcus & Haldane, Andy & Hüser, Anne-Caroline, 2021. "Comparing minds and machines: implications for financial stability," Bank of England working papers 937, Bank of England.
    5. Mary Chen & Matthew DeHaven & Isabel Kitschelt & Seung Jung Lee & Martin Sicilian, 2023. "Identifying Financial Crises Using Machine Learning on Textual Data," International Finance Discussion Papers 1374, Board of Governors of the Federal Reserve System (U.S.).
    6. Rastin Matin & Casper Hansen & Christian Hansen & Pia M{o}lgaard, 2018. "Predicting Distresses using Deep Learning of Text Segments in Annual Reports," Papers 1811.05270, arXiv.org.
    7. Paola Cerchiello & Giancarlo Nicola, 2018. "Assessing News Contagion in Finance," Econometrics, MDPI, vol. 6(1), pages 1-19, February.

    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. Samuel Ronnqvist & Peter Sarlin, 2016. "Bank distress in the news: Describing events through deep learning," Papers 1603.05670, arXiv.org, revised Dec 2016.
    2. Sarlin, Peter & von Schweinitz, Gregor, 2021. "Optimizing Policymakers’ Loss Functions In Crisis Prediction: Before, Within Or After?," Macroeconomic Dynamics, Cambridge University Press, vol. 25(1), pages 100-123, January.
    3. Lainà, Patrizio & Nyholm, Juho & Sarlin, Peter, 2015. "Leading indicators of systemic banking crises: Finland in a panel of EU countries," Review of Financial Economics, Elsevier, vol. 24(C), pages 18-35.
    4. von Schweinitz, Gregor & Sarlin, Peter, 2015. "Signaling Crises: How to Get Good Out-of-Sample Performance Out of the Early Warning System," VfS Annual Conference 2015 (Muenster): Economic Development - Theory and Policy 112964, Verein für Socialpolitik / German Economic Association.
    5. Paola Cerchiello & Giancarlo Nicola, 2018. "Assessing News Contagion in Finance," Econometrics, MDPI, vol. 6(1), pages 1-19, February.
    6. Alessi, Lucia & Detken, Carsten, 2018. "Identifying excessive credit growth and leverage," Journal of Financial Stability, Elsevier, vol. 35(C), pages 215-225.
    7. Virtanen, Timo & Tölö, Eero & Virén, Matti & Taipalus, Katja, 2016. "Use of unit root methods in early warning of financial crises," Bank of Finland Research Discussion Papers 27/2016, Bank of Finland.
    8. Samuel Ronnqvist & Peter Sarlin, 2015. "Detect & Describe: Deep learning of bank stress in the news," Papers 1507.07870, arXiv.org.
    9. Daniel O. Beltran & Mohammad R. Jahan-Parvar & Fiona A. Paine, 2021. "Optimizing Credit Gaps for Predicting Financial Crises: Modelling Choices and Tradeoffs," International Finance Discussion Papers 1307, Board of Governors of the Federal Reserve System (U.S.).
    10. Ruoxi Zhang & Xue Li & Satish Chand, 2018. "An Early Warning Of An Impending Currency Crisis In China," The Singapore Economic Review (SER), World Scientific Publishing Co. Pte. Ltd., vol. 64(05), pages 1101-1125, July.
    11. Ruoxi Zhang & Xue Li & Satish Chand, 2019. "An Early Warning Of An Impending Currency Crisis In China," The Singapore Economic Review (SER), World Scientific Publishing Co. Pte. Ltd., vol. 64(05), pages 1101-1125, December.
    12. Behn, Markus & Gross, Marco & Peltonen, Tuomas A., 2016. "Assessing the costs and benefits of capital-based macroprudential policy," ESRB Working Paper Series 17, European Systemic Risk Board.
    13. Zhi-Qiang Jiang & Gang-Jin Wang & Askery Canabarro & Boris Podobnik & Chi Xie & H. Eugene Stanley & Wei-Xing Zhou, 2018. "Short term prediction of extreme returns based on the recurrence interval analysis," Quantitative Finance, Taylor & Francis Journals, vol. 18(3), pages 353-370, March.
    14. Sarlin, Peter & Ramsay, Bruce A., 2014. "Ending over-lending : Assessing systemic risk with debt to cash flow," Research Discussion Papers 11/2014, Bank of Finland.
    15. Quentin Bro de Comères, 2022. "Predicting European Banks Distress Events: Do Financial Information Producers Matter?," Working Papers hal-03752678, HAL.
    16. Oet, Mikhail V. & Gramlich, Dieter & Sarlin, Peter, 2016. "Evaluating measures of adverse financial conditions," Journal of Financial Stability, Elsevier, vol. 27(C), pages 234-249.
    17. Sarlin, Peter & Rönnqvist, Samuel, 2016. "Bank networks from text: interrelations, centrality and determinants," Working Paper Series 1876, European Central Bank.
    18. Tuomas Antero Peltonen & Michela Rancan & Peter Sarlin, 2019. "Interconnectedness of the banking sector as a vulnerability to crises," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 24(2), pages 963-990, April.
    19. Sarlin, Peter & Ramsay, Bruce A., 2014. "Ending over-lending: Assessing systemic risk with debt to cash flow," Bank of Finland Research Discussion Papers 11/2014, Bank of Finland.
    20. Truong, Chi & Sheen, Jeffrey & Trück, Stefan & Villafuerte, James, 2022. "Early warning systems using dynamic factor models: An application to Asian economies," Journal of Financial Stability, Elsevier, vol. 58(C).

    More about this item

    Keywords

    behavioural finance; financial news; deep learning; bank distress; Word2vec.;
    All these keywords.

    JEL classification:

    • C83 - Mathematical and Quantitative Methods - - Data Collection and Data Estimation Methodology; Computer Programs - - - Survey Methods; Sampling Methods
    • C12 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Hypothesis Testing: General
    • E58 - Macroeconomics and Monetary Economics - - Monetary Policy, Central Banking, and the Supply of Money and Credit - - - Central Banks and Their Policies
    • E61 - Macroeconomics and Monetary Economics - - Macroeconomic Policy, Macroeconomic Aspects of Public Finance, and General Outlook - - - Policy Objectives; Policy Designs and Consistency; Policy Coordination
    • G02 - Financial Economics - - General - - - Behavioral Finance: Underlying Principles
    • G14 - Financial Economics - - General Financial Markets - - - Information and Market Efficiency; Event Studies; Insider Trading

    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:pav:demwpp:demwp0140. 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: Alice Albonico (email available below). General contact details of provider: https://edirc.repec.org/data/dppavit.html .

    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.