Abstract
Motivated by the successful usage of machine learning around computer science and its wide acceptance from the finance literature, we utilize monthly data spanning the period 2008–2018 for the Euro area peripheral countries, in order to embark on a two-fold mission. First, to construct short-term prediction models for bank deposit flows in the Euro area peripheral countries, employing machine learning techniques. Second, to examine whether textual features enhance the predictive ability of our models. From the variety of models tested, we find that Random Forest models including both textual features and macroeconomic variables outperform models including only macro factors or textual features. Monetary policy authorities or macroprudential regulators could adopt our approach to timely predict potential excessive bank deposit outflows and assess the resilience of the whole banking sector in the Euro area peripheral countries.
Similar content being viewed by others
Data availability
Data are not publicly available due to ethical reasons, though the data may be made available on request from the corresponding author.
Notes
We have collected the speeches directly from the website of the ECB. In our sample, there are merely those speeches that are in English language. We acknowledge that there are other potential sources of country-specific macroeconomic news that could be considered. However, we believe that the speeches of the ECB president are the most relevant and influential source of information for the Euro area peripheral countries. The ECB is the primary monetary authority for these countries, and their policies and communications have a significant impact on the overall economic environment. Moreover, the ECB president’s speeches are carefully crafted to communicate the central bank’s policies and intentions, making them an essential source of information for forecasting bank deposit flows. Additionally, the ECB’s commitment to transparency and accountability ensures that market participants closely monitor and analyze these speeches.
As for the computing environment we use, the algorithms were run through Google Colab, a product of Google Research, which allows anyone to write and run arbitrary Python code. Notably, the machine learning algorithms are implemented via the scikit-learn library.
Feed-forward neural networks are networks with fully-connected layers. Namely, each neuron is linked to all of the neurons in the next layer.
This set is practically used to assess the out-of-sample and out-of-time performance of our classifiers.
The macro average approach just sums the measure scores for inflows and outflows, and finally, it divides the result by two.
As an alternative to ensemble modeling, we examine the XG boosting model. In untabulated results, we find that RF achieves better scores in our task.
Anastasiou and Drakos (2021b) found that depositors have lower confidence in the peripheral countries’ banking systems, making the latter suffer from larger deposit outflows (especially in crisis periods), leading to more frequent panics in bank deposits and thus financial instability in the periphery. All these, in turn, further deteriorate agents’ trust in the domestic banking system, which may lead them to rely more on sentiment than macro-financial factors (fundamentals).
References
Ambrose, B. W., & Megginson, W. L. (1992). The role of asset structure, ownership structure, and takeover defenses in determining acquisition likelihood. Journal of Financial and Quantitative Analysis, 27, 575–589.
Anastasiou, D., & Drakos, K. (2021a). Nowcasting the Greek (semi-) deposit run: Hidden uncertainty about the future currency in a Google search. International Journal of Finance and Economics, 26, 1133–1150.
Anastasiou, D., & Drakos, K. (2021b). European depositors’ behavior and crisis sentiment. Journal of Economic Behavior and Organization, 184, 117–136.
Anastasiou, D., & Katsafados, A. (2023). Bank deposits and textual sentiment: When an European Central Bank president’s speech is not just a speech. Manchester School, 91, 55–87.
Anastasiou, D., & Petralias, A. (2021). On the construction of a leading Indicator based on News headlines for Predicting Greek Deposit outflows. International Journal of Business Management and Finance Research, 4(1), 1–11.
Anastasiou, D., Louri, H., & Tsionas, M. (2019). Non-performing loan in the Euro area: Are core-periphery Banking Markets Fragmented? International Journal of Finance and Economics, 24, 97–112.
Anastasiou, D., Kapopoulos, P., & Zekente, K. M. (2022a). Sentimental Shocks and House Prices. Journal of Real Estate Finance and Economics.
Anastasiou, D., Kallandranis, C., & Drakos, K. (2022b). Borrower discouragement prevalence for eurozone SMEs: Investigating the impact of economic sentiment. Journal of Economic Behavior and Organization, 194, 161–171.
Angelopoulou, E., Balfoussia, H., & Gibson, H. D. (2014). Building a financial conditions index for the euro area and selected euro area countries: What does it tell us about the crisis? Economic Modelling, 38, 392–403.
Balakrishnan, R., Qiu, X. Y., & Srinivasan, P. (2010). On the predictive ability of narrative disclosures in annual reports. European Journal of Operational Research, 202, 789–801.
Beaupain, R., & Girard, A. (2020). The value of understanding central bank communication. Economic Modelling, 85, 154–165.
Bijsterbosch, Μ., & Falagiarda, Μ. (2015). The macroeconomic impact of financial fragmentation in the euro area: Which role for credit supply? Journal of International Money and Finance, 54, 93–115.
Birim, S., Kazancoglu, I., Mangla, S. K., Kahraman, A., & Kazancoglu, Y. (2022). The derived demand for advertising expenses and implications on sustainability: A comparative study using deep learning and traditional machine learning methods. Annals of Operations Research, 1–31.
Bodnaruk, A., Loughran, T., & McDonald, B. (2015). Using 10-K text to gauge financial constraints. Journal of Financial and Quantitative Analysis, 50, 623–646.
Boehm, T. P., & DeGennaro, R. P. (2011). A discrete choice model of dividend reinvestment plans: Classification and prediction. Managerial and Decision Economics, 32, 215–229.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24, 123–140.
Brown, S. V., & Tucker, J. W. (2011). Large-sample evidence on firms’ firms’ year-over-year MD&A modifications. Journal of Accounting Research, 49, 309–346.
Cao, L. (2003). Support vector machines experts for time series forecasting. Neurocomputing, 51, 321–339.
Demirguç-Kunt, A., & Detragiache, E. (1998). The determinants of banking crises in developing and developed countries. International Monetary Fund Staff Papers, 45, 81–109.
Dosdogru, A. T. (2019). Comparative study of hybrid artificial neural network methods under stationary and nonstationary data in stock market. Managerial and Decision Economics, 40, 460–471.
Doumpos, M., Andriosopoulos, K., Galariotis, E., Makridou, G., & Zopounidis, C. (2017). Corporate failure prediction in the European energy sector: A multicriteria approach and the effect of country characteristics. European Journal of Operational Research, 262, 347–360.
Espahbodi, H., & Espahbodi, P. (2003). Binary choice models for corporate takeover. Journal of Banking and Finance, 27, 549–574.
Finger, M. H., & Hesse, H. (2009). Lebanon-determinants of commercial bank deposits in a regional financial center. International Monetary Fund, No. 9–195.
Gaganis, C., Pasiouras, F., & Tzanetoulakos, A. (2005). A comparison and integration of classification techniques for the prediction of small UK firms failure. Journal of Financial Decision Making, 1, 55–69.
Galariotis, E. C., Makrichoriti, P., & Spyrou, S. (2016). Sovereign CDS spread determinants and spill-over effects during financial crisis: A panel VAR approach. Journal of Financial Stability, 26, 62–77.
Gandhi, P., Loughran, T., & McDonald, B. (2019). Using annual report sentiment as a proxy for financial distress in U.S. banks. Journal of Behavioral Finance, 20, 424–436.
Geng, R., Bose, I., & Chen, X. (2015). Prediction of financial distress: An empirical study of listed Chinese companies using data mining. European Journal of Operational Research, 241, 236–247.
Goldberg, Y. (2017). Neural network methods for natural language processing. Morgan & Claypool.
Gómez-Puig, M., Sosvilla-Rivero, S., & del Carmen Ramos-Herrera, M. (2014). An update on EMU sovereign yield spread drivers in times of crisis: A panel data analysis. The North American Journal of Economics and Finance, 30, 133–153.
Hagenau, M., Liebmann, M., & Neumann, D. (2013). Automated news reading: Stock price prediction based on financial news using context-capturing features. Decision Support Systems, 55, 685–697.
Hao, J., He, F., Ma, F., Zhang, S., & Zhang, X. (2023). Machine learning vs deep learning in stock market investment: An international evidence. Annals of Operations Research, 1–23.
Hondroyiannis, G. (2004). Estimating private savings behaviour in Greece. Journal of Economic Studies, 31, 457–476.
Huang, W., Nakamori, Y., & Wang, S. Y. (2005). Forecasting stock market movement direction with support vector machine. Computers and Operations Research, 32, 2513–2522.
Huo, D., & Chaudhry, H. R. (2021). Using machine learning for evaluating global expansion location decisions: An analysis of Chinese manufacturing sector. Technological Forecasting and Social Change, 163, 120436.
Ibrahim, B. A., Elamer, A. A., & Abdou, H. A. (2022). The role of cryptocurrencies in predicting oil prices pre and during COVID-19 pandemic using machine learning. Annals of Operations Research, 1–44.
Iworiso, J., & Vrontos, S. (2020). On the directional predictability of equity premium using machine learning techniques. Journal of Forecasting, 39, 449–469.
Janitza, S., Tutz, G., & Boulesteix, A. L. (2016). Random forest for ordinal responses: Prediction and variable selection. Computational Statistics & Data Analysis, 96, 57–73.
Jiang, M., Jia, L., Chen, Z., & Chen, W. (2022). The two-stage machine learning ensemble models for stock price prediction by combining mode decomposition, extreme learning machine and improved harmony search algorithm. Annals of Operations Research, 309, 553–585.
Kamble, S. S., Gunasekaran, A., Kumar, V., Belhadi, A., & Foropon, C. (2021). A machine learning based approach for predicting blockchain adoption in supply chain. Technological Forecasting and Social Change, 163, 120465.
Katsafados, A. G., Androutsopoulos, I., Chalkidis, I., Fergadiotis, E., Leledakis, G. N., & Pyrgiotakis, E. G. (2021). Using textual analysis to identify merger participants: Evidence from U.S. banking industry. Finance Research Letters, 42, 101949.
Katsafados, A. G., Leledakis, G. N., Pyrgiotakis, E. G., Androutsopoulos, I., Chalkidis, I., & Fergadiotis, M. (2023a). Textual information and IPO underpricing: A machine learning approach. Journal of Financial Data Science, 5, 100–135.
Katsafados, A. G., Nikoloutsopoulos, S., & Leledakis, G. N. (2023b). Twitter sentiment and stock market: A COVID-19 analysis. Journal of Economic Studies, forthcoming.
Katsafados, A. G., Leledakis, G. N., Pyrgiotakis, E. G., Androutsopoulos, I., & Fergadiotis, E. (2024). Machine learning in US bank merger prediction: A text-based approach. European Journal of Operational Research, 312, 783–797.
Kearney, C., & Liu, S. (2014). Textual sentiment in finance: A survey of methods and models. International Review of Financial Analysis, 33, 171–185.
Kim, A., & Kim, H. (2022). A new classification tree method with interaction detection capability. Computational Statistics & Data Analysis, 165, 107324.
Kumar, B. S., & Ravi, V. (2016). A survey of the applications of text mining in financial domain. Knowledge-Based Systems, 114, 128–147.
Kumar, R. B., Kumar, B. S., & Prasad, C. S. S. (2012). Financial news classification using SVM. International Journal of Scientific and Research Publications, 2, 2250–3153.
Li, J. P., Mirza, N., Rahat, B., & Xiong, D. (2020). Machine learning and credit ratings prediction in the age of fourth industrial revolution. Technological Forecasting and Social Change, 161, 120309.
Loughran, T., & McDonald, Β. (2013). IPO first-day returns, offer price revisions, volatility, and form S-1 language). Journal of Financial Economics, 109, 307–326.
Loughran, T., & McDonald, B. (2016). Textual analysis in accounting and finance: A survey. Journal of Accounting Research, 54, 1187–1230.
Mai, F., Tian, S., Lee, C., & Ma, L. (2019). Deep learning models for bankruptcy prediction using textual disclosures. European Journal of Operational Research, 274, 743–758.
Martinez-Peria, M. S., & Schmukler, S. L. (2001). Do depositors punish banks for bad behavior? Market discipline, deposit insurance, and banking crisis. Journal of Finance, 56, 1029–1051.
Min, J. H., & Lee, Y. C. (2005). Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Systems with Applications, 28, 603–614.
Moniz, A., & Jong, F. D. (2014). Classifying the influence of negative affect expressed by the financial media on investor behavior. 5th Information Interaction in Context Symposium (IIiX), 275–278.
Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., & Ling Ngo, D. C. (2014). Text mining for market prediction: A systematic review. Expert Systems with Applications, 41, 7653–7670.
Nys, E., Tarazi, A., & Trinugroho, I. (2015). Political connections, bank deposits, and formal deposit insurance. Journal of Financial Stability, 19, 83–104.
Oliveira, R., Schiozer, R. F., & Barros, L. (2014). Depositors’ perception of too-big-to-fail. Review of Finance, 18, 1–37.
Pai, P. F., & Lin, C. S. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega, 33, 497–505.
Palepu, K. G. (1986). Predicting takeover targets: A methodological and empirical analysis. Journal of Accounting and Economics, 8, 3–35.
Papoulias, C., & Theodossiou, P. (1992). Analysis and modeling of recent business failures in Greece. Managerial and Decision Economics, 13, 163–169.
Pasiouras, F., & Tanna, S. (2010). The prediction of bank acquisition targets with discriminant and logit analyses: Methodological issues and empirical evidence. Research in International Business and Finance, 24, 39–61.
Pasiouras, F., Tanna, S., & Zopounidis, C. (2007). The identification of acquisition targets in the EU banking industry: An application of multicriteria approaches. International Review of Financial Analysis, 16, 262–281.
Pasiouras, F., Gaganis, C., Tanna, S., & Zopounidis, C. (2008). An application of support vector machines in the prediction of acquisition targets: Evidence from the EU banking sector). In C. Zopounidis, M. Doumpos, & P. Pardalos (Eds.), Handbook of Financial Engineering. Springer.
Pasiouras, F., Gaganis, S., & Zopounidis, C. (2010). Multicriteria classification models for the identification of targets and acquirers in the Asian banking sector. European Journal of Operational Research, 204, 328–335.
Pestov, V. (2013). Is the k-NN classifier in high dimensions affected by the curse of dimensionality? Computers and Mathematics with Applications, 65, 1427–1437.
Petropoulos, A., Vlachogiannakis, N. E., & Mylonas, D. (2018). Forecasting private sector bank deposits in Greece: Determinants for trend and shock effects. International Journal of Banking Accounting and Finance, 9, 141–169.
Piscopo, G. (2010). Italian deposits time series forecasting via functional data analysis. Banks and Bank Systems, 5, 12–19.
Quintana, D., Sáez, Y., & Isasi, P. (2017). Random forest prediction of IPO underpricing. Applied Sciences, 7, 636.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should i trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135–1144).
Routledge, B. R., Sacchetto, S., & Smith, N. A. (2017). Predicting merger targets and acquirers from text. Working Paper, Carnegie Mellon University.
Sariannidis, N., Papadakis, S., Garefalakis, A., Lemonakis, C., & Kyriaki-Argyro, T. (2020). Default avoidance on credit card portfolios using accounting, demographical and exploratory factors: Decision making based on machine learning (ML) techniques. Annals of Operations Research, 294, 715–739.
Shin, K. S., Lee, T. S., & Kim, H. (2005). An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications, 28, 127–135.
Stevenson, M., Mues, C., & Bravo, C. (2021). The value of text for small business default prediction: A deep learning approach. European Journal of Operational Research, 295, 758–771.
Sun, S., Luo, C., & Chen, J. (2017). A review of natural language processing techniques for opinion mining systems. Information Fusion, 36, 10–25.
Tang, X., Li, S., Tan, M., & Shi, W. (2020). Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods. Journal of Forecasting, 39, 769–787.
Vapnik, V. N., & Vapnik, V. (1998). Statistical learning theory: 1. Wiley.
Veganzones, D., & Severin, E. (2018). An investigation of bankruptcy prediction in imbalanced datasets. Decision Support Systems, 112, 111–124.
Wu, C. H., Tzeng, G. H., Goo, Y. J., & Fang, W. C. (2007). A real-valued genetic algorithm to optimize the parameters of support vector machine for predicting bankruptcy. Expert Systems with Applications, 32, 397–408.
Zhao, S., Xu, K., Wang, Z., Liang, C., Lu, W., & Chen, B. (2022). Financial distress prediction by combining sentiment tone features. Economic Modelling, 106, 105709.
Zoricak, M., Gnip, P., Drotar, P., & Gazda, V. (2020). Bankruptcy prediction for small-and medium-sized companies using severely imbalanced datasets. Economic Modeling, 84, 165–176.
Funding
This research received no external funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
The views and opinions expressed herein are those of the authors and do not reflect their respective institutions.
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Katsafados, A.G., Anastasiou, D. Short-term prediction of bank deposit flows: do textual features matter?. Ann Oper Res (2024). https://doi.org/10.1007/s10479-024-06048-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10479-024-06048-8