Forecasting Bank Capital Ratios Using the Prophet Model by Facebook
DOI:
https://doi.org/10.58886/jfi.v20i3.4941Abstract
This study investigates the efficacy of the Prophet model by Facebook with respect to forecasting bank capital ratios. Bank financial ratios and macroeconomic information are combined to forecast total risk-adjusted capital ratios for 19 large U.S. banks. Using a sample period from March 2005 to December 2020, in-sample results show that the model accurately estimates bank capital ratios over time. As validation, out-of-sample tests indicate that forecasting errors are smaller for Prophet models compared to benchmark ARIMAX models. Based on these and other results, we conclude that the Prophet model does a good job of forecasting bank capital ratios. By implication, it provides a practical forecasting tool for bank regulatory supervisors, management, and investors.
References
Acharya, V. V, and Steffen, S. (2014a). Benchmarking the European Central Bank’s asset quality review and stress test: A tale of two leverage ratios. VOX CEPR’s Policy Portal.
Acharya, V. V, and Steffen, S. (2014b). Making sense of the comprehensive assessment. Working paper, CEPR, NYU Stern, and ESMT European School of Management and Technology.
Acharya, V. V., Berger, A. N., and Roman, R. A. (2018). Lending implications of U.S. bank stress tests: Costs or benefits? Journal of Financial Intermediation 34, 58–90. DOI: https://doi.org/10.1016/j.jfi.2018.01.004
Acharya, V., R. Engle, and M. Richardson (2012). Capital shortfall: A new approach to ranking and regulating systematic risks. American Economic Review102, 59–64. DOI: https://doi.org/10.1257/aer.102.3.59
Agrawal, T. (2021). Hyperparameter Optimization in Machine Learning: Make Your Machine Learning and Deep Learning Models More Efficient. Apress, Springer Nature: Berlin, Germany. DOI: https://doi.org/10.1007/978-1-4842-6579-6
Altman, E. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance 23, 189–209. DOI: https://doi.org/10.2307/2978933
Altman, E., Haldeman, R., and Narayanan, P. (1977). ZETA analysis: A new model to identify bankruptcy risk of corporations. Journal of Banking and Finance 1, 29–54. DOI: https://doi.org/10.1016/0378-4266(77)90017-6
Altman, E. I., and McGough, T. P. (1974). Evaluation of a company as a going concern. Journal of Accounting 138, 50–57.
Alves, C., Mendes, V., and Pereira Da Silva, P. (2015). Do stress tests matter? A study on the impact of the disclosure of stress test results on European financial stocks and CDS markets. Applied Economics 47, 1213–1229. DOI: https://doi.org/10.1080/00036846.2014.993132
Arena, M. (2008). Bank failures and bank fundamentals: A comparative analysis of Latin America and East Asia during the nineties using bank-level data. Journal of Banking and Finance 32, 299–310. DOI: https://doi.org/10.1016/j.jbankfin.2007.03.011
Berger, A. N., Imbierowicz, B., and Rauch, C. (2016). The roles of corporate governance in bank failures during the recent financial crisis. Journal of Money, Credit and Banking 48, 729–770. DOI: https://doi.org/10.1111/jmcb.12316
Betz, F., Oprică, S., Peltonen, T. A., and Sarlin, P. (2014). Predicting distress in European banks. Journal of Banking and Finance 45, 225–241. DOI: https://doi.org/10.1016/j.jbankfin.2013.11.041
Bovenzi, J. F., Marino, J. A., and McFadden. E. F. (1983). Commercial bank failure prediction models. Economic Review, Federal Reserve Bank of Atlanta, 186–195.
Box, G. E. P., Jenkins, G. M., and Reinsel, G. C. (2011). Time Series Analysis, Forecasting and Control, 4th ed. Wiley: Hoboken, NJ.
Boyacioglu, M. A., Kara, Y., and Baykan, M. K. (2009). Predicting bank financial failures using neural networks, support vector machines and multivariate statistical methods: A comparative analysis in the sample of savings deposit insurance fund (SDIF) transferred banks in Turkey. Expert Systems with Applications 36, 3355–3366. DOI: https://doi.org/10.1016/j.eswa.2008.01.003
Chapel, A., Killgo, K., and Klemme, K. (2021) Banks face new challenges as Texas rebounds from COVID-19 shock. Southwest Economy, Federal Reserve Bank of Dallas, 14–17.
Chernykh, L., and Cole, R. A. (2015). How should we measure bank capital adequacy for triggering prompt corrective action? A (simple) proposal. Journal of Financial Stability 20, 131–143. DOI: https://doi.org/10.1016/j.jfs.2015.08.003
Cheung, Y. W., Chinn, M. D., and Pascual, A. G. (2005). What do we know about recent exchange rate models? In-sample fit and out-sample performance evaluated. In Exchange Rate Modelling: Where Do We Stand? DeGrauwe P., Ed.. MIT Press: Cambridge, MA, 239–276 DOI: https://doi.org/10.7551/mitpress/2897.003.0011
Chiaramonte, L., and Casu, B. (2017). Capital and liquidity ratios and financial distress. Evidence from the European banking industry. The British Accounting Review 49, 138–161. DOI: https://doi.org/10.1016/j.bar.2016.04.001
Chiaramonte, L., Liu, F. H., Poli, F., and Zhou, M. (2016). How accurately can Z-score predict bank failure? Financial Markets, Institutions and Instruments 25, 333–360. DOI: https://doi.org/10.1111/fmii.12077
Coats, P. K., and Fant, L. F. (1993). Recognizing financial distress patterns using a neural network tool. Financial Management 22, 142–155. DOI: https://doi.org/10.2307/3665934
Cole, R. A., and Wu, Q. (2009). Predicting bank failures using a simple dynamic hazard model. Paper presented at 22nd Australasian Finance and Banking Conference, Sydney, Australia.
Covas, R., and Driscoll, J. C. (2014). Bank liquidity and capital regulation in general equilibrium, Working paper 2014-85, Federal Reserve Board, Washington, D.C. DOI: https://doi.org/10.2139/ssrn.2495581
DeAngelo, H., and DeAngelo, L. (1990). Dividend policy and financial distress: An empirical investigation of NYSE firms. Journal of Finance 45, 1415–1431. DOI: https://doi.org/10.1111/j.1540-6261.1990.tb03721.x
Ekinci, A., and Erdal, H. E. (2016). Forecasting bank failure: Base learners, ensembles and hybrid ensembles. Computational Economics 49, 677–686. DOI: https://doi.org/10.1007/s10614-016-9623-y
Facebook. (2017). Facebook Prophet documentation. https://facebook.github.io/prophet.
Fang, W. X., Lan, P. C., Lin, W. R., Chang, H. C., Chang, H. Y., and Wang, Y. H. (2019). Combine Facebook prophet and LSTM with BPNN forecasting financial markets: The Morgan Taiwan Index. Proceedings of the 2019 International Symposium on Intelligent Signal Processing and Communication Systems, Taipei, Taiwan, 1–2. DOI: https://doi.org/10.1109/ISPACS48206.2019.8986377
Georgescu, O. M., Gross, M., Kapp, D., and Kok, C. (2017). Do stress tests matter? Evidence from the 2014 and 2016 stress tests. Working paper no. 2054, European Central Bank. DOI: https://doi.org/10.2139/ssrn.2968952
Gilbert, R. A., Meyer, A. P., and Vaughn, M. D. (1999). The role of supervisory screens and econometric models in off-site surveillance. Review, Federal Reserve Bank of St. Louis (November/December), 31–56.
Glasserman, P., and Tangirala, G. (2016). Are the Federal Reserve’s stress test results predictable? Journal of Alternative Investments 18, 82–97. DOI: https://doi.org/10.3905/jai.2016.18.4.082
Goel, T., and Agarwal, I. (2021). Limits of stress-test based bank regulation. BIS Working paper no. 953, Monetary and Economic Department, Bank for International Settlements. DOI: https://doi.org/10.2139/ssrn.3712632
Güleryüz, D., and Özden, E. (2020). The prediction of brent crude oil trend using LSTM and facebook Prophet. Avrupa Bilim ve Teknoloji Dergisi 20, 1–9.
Hastie, T., and Tibshirani, R. (1986). Generalized additive models. Statistical Science 1, 297–310. DOI: https://doi.org/10.1214/ss/1177013604
Hirtle, B., Kovner, A., Vickery, J., and Bhanot, M. (2016). Assessing financial stability: The capital and loss assessment under stress scenarios (CLASS) model. Journal of Banking and Finance 69, 35–55. DOI: https://doi.org/10.1016/j.jbankfin.2015.09.021
Homar, T., Kick, H., and Salleo, C. (2016). Making sense of the EU wide stress test: A comparison with the SRISK approach. Working paper no. 1920. European Central Bank. DOI: https://doi.org/10.2139/ssrn.2797376
Hyndman R., and Khandakar, Y. (2008). Automatic time series forecasting: The forecast package for R. Journal of Statistical Software 27, 1-22. DOI: https://doi.org/10.18637/jss.v027.i03
Iyengar, G., Luo, Y., Rajgopal, S., Venkatasubramanian, V., and Zhang, Z. (2017). Towards a financial statement based approach to modeling systemic risk in insurance and banking. Working paper no. 17–77, Columbia Business School.
Iwanicz-Drozdowska, M., Laitinen, E. K., and Suvas, A. (2018). Paths of glory or paths of shame? An analysis of distress events in European banking. Bank i Kredyt 49, 115–144.
Jagtiani, J. A., Kolari, J. W., Lemieux, C. M., and Hwan Shin, G. H. (2000). Predicting inadequate capitalization: Early warning system for bank supervision. Emerging Market Series (S&R-2000-10R), Federal Reserve Bank of Chicago (September).
Jha, B. K., and Pande, S. (2021). Time series forecasting model for supermarket sales using FB-Prophet. Paper presented at the 2021 5th International Conference on Computing Methodologies and Communication, Erode, India, 547-554. DOI: https://doi.org/10.1109/ICCMC51019.2021.9418033
Jing, Z., and Fang, Y. (2017). Predicting US bank failures: A comparison of logit and data mining models. Journal of Forecasting 37, 235–256. DOI: https://doi.org/10.1002/for.2487
Johnsen, T., and Melicher, R. W. (1994). Predicting corporate bankruptcy and financial distress: Information value added by multinomial logit models. Journal of Economics and Business 46, 269–286. DOI: https://doi.org/10.1016/0148-6195(94)90038-8
Kapinos, P., and Mitnik, O. A. (2016). A top-down approach to stress-testing banks. Journal of Financial Services Research 49, 229–264. DOI: https://doi.org/10.1007/s10693-015-0228-8
Kolari, J., Glennon, D., Shin, H., & Caputo, M. (2002). Predicting large US commercial bank failures. Journal of Economics and Business 54, 361–387. DOI: https://doi.org/10.1016/S0148-6195(02)00089-9
Kolari, J. W., López-Iturriaga, F. J. L., and Sanz, I. P. (2019). Predicting stress tests in European banks. Global Finance Journal 39, 44–57. DOI: https://doi.org/10.1016/j.gfj.2018.01.015
Korobrow, L., and Stuhr, D. (1985). Performance measurement of early warning models: Comments on West and other weakness/failure prediction models. Journal of Banking and Finance 9, 267–273. DOI: https://doi.org/10.1016/0378-4266(85)90022-6
Kumar, N., Chauhan, R., and Dubey, G. (2019). Applicability of financial system using deep learning techniques. Proceedings of the 2019 International Conference on Recent Advancement in Computer, Communication and Computational Sciences. Springer: Berlin, Germany. DOI: https://doi.org/10.1007/978-981-15-1518-7_11
López-Iturriaga, F. J., and Sanz, I. P. (2015). Bankruptcy visualization and prediction using neural networks: A study of U.S. commercial banks. Expert Systems with Applications 42, 2857–2869. DOI: https://doi.org/10.1016/j.eswa.2014.11.025
Madhuri, C., Chinta, M., and Kumar, V. (2020). Stock market prediction for time-series forecasting using Prophet upon ARIMA. Paper presented at the 7th International Conference on Smart Structures and Systems (ICSSS), Chennai, India, 317–321. DOI: https://doi.org/10.1109/ICSSS49621.2020.9202042
Mahanty, M., Swathi, K., Teja, K. S., Kumar, P. H., and Sravani, A. (2021). Forecasting the spread of COVID-19 pandemic with Prophet. Revue d'Intelligence Artificielle 35, 115–122. DOI: https://doi.org/10.18280/ria.350202
Mahmud, S. (2020). Bangladesh COVID-19 daily cases time series analysis using Facebook Prophet model. Working paper, Shahjalal University of Science and Technology. DOI: https://doi.org/10.2139/ssrn.3660368
Maldonado, S., Gonzalez, A., and Crone, S. (2019). Automatic time series analysis for electric load forecasting via support vector regression. Applied Soft Computing 83, 105616. DOI: https://doi.org/10.1016/j.asoc.2019.105616
Martínez, I. (1996). Forecasting company failure: neural approach versus discriminant analysis: An application to Spanish insurance companies. In Intelligent Systems in Accounting and Finance. Sierra Molina, G., and Bonsón Ponte, E. (Eds.). Huelva: Spain, 169–185.
Meyer, P. and Pifer, H. (1970). Prediction of bank failures. Journal of Finance 25, 853–868. DOI: https://doi.org/10.1111/j.1540-6261.1970.tb00558.x
Oliveira, E. M., and Oliveira, F .L. (2018). Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods. Energy 144, 776–788. DOI: https://doi.org/10.1016/j.energy.2017.12.049
Ömer Faruk D. (2010). A hybrid neural network and ARIMA model for water quality time series prediction. Engineering Applications of Artificial Intelligence 23, 586–594. DOI: https://doi.org/10.1016/j.engappai.2009.09.015
Pritsker, M. (2014). Stress-testing US bank holding companies: A dynamic panel quantile regression approach: A comment. International Journal of Forecasting 30, 714–716. DOI: https://doi.org/10.1016/j.ijforecast.2013.11.004
Sahin, C., de Haan, J., and Neretina, E. (2020). Banking stress test effects on returns and risks. Journal of Banking and Finance 117, 1–19. DOI: https://doi.org/10.1016/j.jbankfin.2020.105843
Schuermann, T. (2020). Capital adequacy pre‐ and postcrisis and the role of stress testing. Journal of Money, Credit and Banking 52, 87–105. DOI: https://doi.org/10.1111/jmcb.12735
Shradha S., Joshi, J., Mareedu, S., Kim, Y. P., and Woo, J. (2021). Scalable predictive time-series analysis of COVID-19: Cases and fatalities. Working paper, Cornell University.
Sinkey, J. E., Jr. (1975). A multivariate statistical analysis of the characteristics of problem banks. Journal of Finance 20, 21–36. DOI: https://doi.org/10.1111/j.1540-6261.1975.tb03158.x
Svetunkov, I. (2020). Time Series Analysis and Forecasting with ADAM. URL: openforecast.org/adam (April 2021).
Tam, K.Y., and Kiang, M. (1992). Predicting bank failures: A neural network approach. Decision Sciences 3, 926–947. DOI: https://doi.org/10.1287/mnsc.38.7.926
Taylor, S. J., and Letham, B. (2018). Forecasting at scale. The American Statistician 72, 37–45. DOI: https://doi.org/10.1080/00031305.2017.1380080
Valencia, F., and Laeven, L. (2008). Systemic banking crises: A new database. IMF Working paper no. 08(224). DOI: https://doi.org/10.5089/9781451870824.001
Vellido, A. (1999). Neural networks in business: a survey of applications (1992–1998). Expert Systems with Applications 17, 51–70. DOI: https://doi.org/10.1016/S0957-4174(99)00016-0
Whalen, G., and Thomson, J. B. (1988). Using financial data to identify changes in bank condition. Economic Review, Federal Reserve Bank of Cleveland, 17–26.
