CLOUD COMPUTING AND SELECTED MODELS OF DEEP LEARNING IN BANKING

• Authors: Balicka Honorata

Title variants

EN

CHMURY OBLICZENIOWE ORAZ WYBRANE ZASTOSOWANIA UCZENIA GŁĘBOKIEGO W BANKACH

• Languages of publication: PL EN

Abstracts

PL

Współczesne zagrożenia systemu bankowego wynikają z rozwoju kryptowalut, a szczególnie Bitcoina, co jest sprzeczne z podstawami bankowości, gdyż pomija się przede wszystkim rolę banków centralnych. Ponadto kryzys gospodarczy związany z panującą powszechnie pandemią może wywołać poważny kryzys finansowy, a nawet bankowy. Warto zatem zastanowić się nad możliwością pokonania powstałych zagrożeń przez banki. Celem pracy jest scharakteryzowanie kierunków rozwoju bankowości w zakresie stosowania nowoczesnych technologii informatycznych opierających się na chmurach obliczeniowych oraz głębokich sieciach neuronowych. Zdaniem Autorki właśnie taka strategia stwarza duże szanse na uniknięcie poważnego kryzysu bankowego z powodu rozwoju pandemii oraz kryptowalut. W artykule omówiono wybrane modele zastosowania chmur obliczeniowych oraz deep learningu w bankowości. Zaproponowane modele uczenia głębokiego cechują się istotnym potencjałem w zakresie wzrostu konkurencyjności przedsiębiorstw bankowych. Wymagają jednak efektywnego wykorzystania superkomputerów i chmur obliczeniowych w procesie długotrwałego treningu tej klasy aplikacji informatycznych. W szczególności scharakteryzowano klasyfikację wniosków kredytowych, przewidywanie kryzysu bankowego, a także przewidywanie kursów walut na giełdzie papierów wartościowych. Tak rozumiana inteligentna chmura bankowa umożlwia skuteczne konkurowanie w warunkach rozwijających się globalnie gospodarek opartych na wiedzy i nowoczesnych technologiach. Szczegónie w obecnych warunkach kryzysu gospodarczego wywołanego przez pandemię Covid-19 kluczowe znaczenie odgrywa szybkość reakcji i działania na zmieniające się waunki popytu. Trafne podejmowanie decyzji finansowych w warunkach rozległego i głębokiego kryzysu także na rynku pracy może być zrealizowane za pomocą inteligentnego przetwarzania dużej ilości różnorodnych danych (Big Data). Właściwymi metodami są zwłaszcza metody uczenia maszynowego wykorzystane w środowisku chmur obliczeniowych. Z tego powodu omówiono wybrane aspekty precyzyjnego podejmowania decyzji w relatywnie krótkim czasie w bankowości.

EN

Contemporary threats to the banking system result from the development of cryptocurrencies, especially Bitcoin, which is contrary to the basics of banking, as the role of central banks is largely ignored. In addition, the economic crisis associated with a widespread pandemic could trigger a severe financial and even banking crisis. It is therefore worth considering the possibility of banks overcoming the threats that have arisen. The aim of the work is to characterize the directions of banking development in the field of using modern information technologies based on cloud computing and deep neural networks. According to the author, such a strategy creates a great chance to avoid a serious banking crisis due to the development of the pandemic and cryptocurrencies.This article discusses selected models of cloud computing and deep learning in banking. The proposed deep learning models have a significant potential to increase the competitiveness of banking enterprises. However, they require the effective use of supercomputers and cloud computing in the process of long-term training of this class of IT applications. In particular, the classification of loan applications, forecasting a banking crisis, as well as forecasting exchange rates on the stock exchange are characterized. Intelligent banking cloud enables effective competition in the conditions of globally developing economies based on knowledge and modern technologies. Especially, in the current economic crisis triggered by the Covid-19 pandemic, speed of response and response to changing demand conditions is crucial. Accurate financial decision-making in the conditions of a widespread and deep crisis, also in the labor market with access, can be achieved through intelligent processing of large amounts of various data (Big Data). In particular, machine learning methods used in the cloud computing environment are appropriate methods. For this reason, selected aspects of precise decision making in a relatively short time in banking were discussed.

Keywords

PL

bankowość, uczenie głębokie, sztuczne sieci neuronowe

EN

banking, deep learning, artificial neural networks

• Publisher: Sopocka Akademia Nauk Stosowanych
• Journal: Przestrzeń, Ekonomia, Społeczeństwo
• Year: 2019
• Issue: 16/II
• Pages: 57-88

Dates

published

2019

Contributors

author

Balicka Honorata

• Sopocka Szkoła Wyższa

References

• Abe Y. et al., Power and performance analysis of GPU-accelerated systems, “Proceedings of the 2012 USENIX Conf. on Power-Aware Computing and Systems (HotPower'12)”, USENIX Association, Berkeley, USA, 2012.
• Aldrich E., Fernández-Villaverde M., Gallant J.R., Rubio-Ramírez A., Juan F., Tapping the supercomputer under your desk: Solving dynamic equilibrium models with graphics processors, “Journal of Economic Dynamics and Control”, Elsevier, vol. 35(3), 2011.
• Baesens B., Setiono R., Mues C., Vanthien J., Using neural network rule extraction and decision tables for credit-risk evaluation, “Management Science”, Vol. 49, No. 3, March 2003.
• Balicka H., Balicki J., Korłub W., Paluszak J., Pastewski M., Przybyłek P., Zadroga M., Zakidalski M., Artificial intelligence methods to support banking information systems, In: K. Kreft, D. Wach, J. Winiarski (eds.): Information systems in the economy, University of Gdańsk Press, Gdańsk 2013.
• Balicka H., Balicki J., Korłub W., Paluszak J., Zadroga M., Supercomputers to support economic processes with particular emphasis on the banking sector, “Contemporary Economy”, Vol. 4, Issue 5, 2014.
• Balicki J., Beringer M., Korłub W., Przybyłek P., Tyszka M., Zadroga M., Collective citizens’ behavior modelling with support of the Internet of Things and Big Data, “Proceedings of the 8th International Conference on Human-System-Interaction HSI’2015”, Warsaw, Poland, June 25-27, 2015.
• Balicki J., Korłub W., Paluszak J., Big data processing by volunteer computing supported by intelligent agents, “Proceedings of 6th International Conference, PReMI 2015, Warsaw, Poland, June 30 - July 3, 2015, Lecture Notes in Computer Science”, Vol. 9124.
• Balicki J., Korłub W., Tyszka M., Harmony search to self-configuration of fault tolerant grids for big data. In: Z. Kowalczuk: “Advances in Intelligent Systems and Computing”, Vol. 386, 2016.
• Balicki J., Multi-criterion decision making by artificial intelligence techniques, “Proceedings on the 8th Int. Con. on Artificial Intelligence, Knowledge Engineering and Data Bases”, February 2009, Cambridge.
• Balicki J., Przybyłek P., Zadroga M., Zakidalski M., Artificial neural networks and the support vector method in banking information systems, “Contemporary Economy”, Vol. 4, 2013.
• Balicki J., Szymański J., Kępa M., Draszawka K., Korłub W., Improving effectiveness of svm classifier for large scale data, “Proceedings on 14th International Conference”, ICAISC 2015, Zakopane, Poland, June 14-18, 2015, “Part I, Lecture Notes in Computer Science”, Vol. 9119.
• Bandi N., Sun C., Agrawal D., El Abbadi A., Hardware acceleration in commercial databases: A case study of spatial operations, 2004.
• Bechler A., Comparison of the effectiveness of neural networks and econometric models in supporting credit decisions, “Application of statistical methods in scientific research”, StatSoft Poland, Cracow 2003.
• Bosse T., Siddiqui G.F., Treur J., Supporting financial decision making by an intelligent agent estimating greed and risk, “Proceedings the IEEE/WIC/ACM Int. Conf. on Web Intelligence and Intelligent Agent Technology”, Vol. 3, Aug. 31-Sept. 3 2010.
• Brown C., Technical analysis for the trading professional, Second Edition: Strategies and techniques for today’s turbulent global financial markets, The McGrawHill Companies, New York 2011.
• Chaveesuk R., Srivaree-Ratana C., Smith A.E., Alternative neural network approaches to corporate bond rating, “Journal of Engineering Valuation and Cost Analysis”, Vol. 2, 1999.
• Chen S.-H., Kuoand T.-W. Hoi K.-M.: Genetic programming and financial trading: How much about "What we Know“. In: “4th NTU International Conference on Economics, Finance and Accounting”, April 2006.
• Davis E. P., Karim D., Comparing early warning systems for banking crises, “Journal of Financial Stability”, Vol. 4, no. 2, 2008.
• Demirguc-Kunt A., Detragiache E., Monitoring banking sector fragility: a multivariate logit approach, “World Bank Economic Review”, Vol. 14, no. 2, 2000.
• Dziubinski M.P., Grassi S., Heterogeneous computing in economics: A Simplified approach, “CREATES Research Papers 2012-15”, School of Economics and Management, University of Aarhus, 2012.
• Frankel J. A., Rose A. K., Currency crashes in emerging markets: an empirical treatment, “Journal of International Economics”, Vol. 41, no. 3-4, 1996.
• Gately E., Neural networks. Financial forecasting and design of transaction systems, WIG-Press, Warsaw 1999.
• Gis A., A multi-threaded application that uses artificial neural networks and a swarm algorithm for prediction on the stock exchange, “Master's thesis”, Gdansk University of Technology, Gdansk 2015.
• Govindaraju N. K., Lloyd B., Wang W., Lin M., Manocha D.: Fast computation of database operations using graphics processors, “Proceedings of the 2004 ACM SIGMOD Int. Conf. on Management of Data”, June 2004.
• Hanschel E., Monnin P.: Measuring and forecasting stress in the banking sector: evidence from Switzerland, “Investigating the Relationship between the Financial and Real Economy”, BIS Papers, no. 22, 2005.
• Henley W.E., Hand D.J., A k-nearest-neighbour classifier for assessing consumer credit risk, “The Statistician”, Vol. 45, Issue 1, 1996.
• Kaminsky G. L., Reinhart C. M., The twin crises: the causes of banking and balance-of-payments problems, “American Economic Review”, Vol. 89, no. 3.
• Leyton-Brown K., Shoham Y., Multiagent systems: algorithmic, game- theoretic, and logical Foundations. “Cambridge University Press”, 2008.
• Majer I.: Application scoring: logit model approach and the divergence method compared, Department of Applied Econometrics, Working Paper, No. 10-06, 2006.
• Mylonakis J., Diacogiannis G., Evaluating the likelihood of using linear discriminant analysis as a commercial bank card owners credit scoring model, International Business Research, Vol. 3, No. 2, 2010.
• Nazari M., Alidadi M., Measuring credit risk of bank customers using artificial neural network, “Journal of Management Research”, Vol. 5, No. 2, 2013.
• Oet M., Eiben R., Bianco T., Gramlich D., Ong S., Wang J., SAFE: an early warning system for systemic banking risk, “Proceedings of the 24th Australasian Finance and Banking Conference”, SSRN, 2011.
• Pandey V., Wee-Keong Ng, Ee-Peng Lim, Financial advisor agent in a multi-agent financial trading system, “Proceedings 11th Int. Workshop on Database and Expert Systems Applications”, 2000.
• Pietrzak E., Markiewicz M. (red.), Finance, banking and financial markets. Publishing House of the University of Gdańsk, Gdansk 2006.
• Potvin J.-Y., Soriano P., Vall M., Generating trading rules on the stock markets with genetic programming. Computers & Operations Research, Vol. 31, 2004.
• Pruitt SW, White RE, The CRISMA trading system: who says technical analysis can’t beat the market?, “Journal of Portfolio Management”, 1988;14:55–8.
• Schwaerzel R., Financial time series prediction and evaluation by genetic programming with trigonometric functions and high-order statistics, “Ph.D. Dissertation”, The University of Texas at San Antonio, Advisor(s) Tom Bylander 2006.
• Shouwei L., Mingliang W., Jianmin H., Prediction of banking systemic risk based on support vector machine, “Mathematical Problems in Engineering”, Vol. 2013, April 2013.
• Solomon S., Option pricing on the GPU, High Performance Computing and Communications, 2010.
• Srivastava R. P., Automating judgmental decisions using neural networks: a model for processing business loan applications, “Proceedings of the 1992 ACM annual conference on Communications”.
• Staniec I., Application of artificial neural networks and selected statistical methods to support credit decisions. Applications of statistical methods in scientific research II, StatSoft Poland, Cracow 2003.
• Svangard N., Nordin P., Lloyd S., Wihlborg C., Evolving short-term trading strategies using genetic programming, “Proceedings of the Congress on Evolutionary Computation”, Vol. 2, 2002.
• Wooldridge M., Introduction to multiagent systems, John Wiley & Sons, June 2002.
• Yobas M.B., Crook J.N., Ross P.: Credit scoring using neural and evolutionary technique,”IMA Journal of Mathematics Applied in Business and Industry”, Vol. 11, 2000.
• Zan H. et al., Credit rating analysis with support vector machines and neural networks: a market comparative study, “Decision Support Systems”, Vol. 37, 2004.
• Benchmark German Credit dataset, http://archive.ics.uci.edu/ml/datasets/Statlog+%28German+Credit+Data%29, [Access: 20.08.2020].
• Bitcoin.org, https://bitcoin.org/en/, [Access: 20.08.2020].
• Bitcoin: A Peer-to-Peer Electronic Cash System, https://bitcoin.org/bitcoin.pdf, [Access: 20.08.2020].
• EBA warns consumers on virtual currencies, http://www.eba.europa.eu/-/eba-warns-consumers-on-virtual-currencies, [Access: 20.01.2021].
• Eurostat. http://ec.europa.eu/eurostat/, [Access: 20.01.2021].
• Forbes, http://www.forbes.com/sites/techonomy/2014/08/07/bitcoin-momentum-grows-in-emerging-markets/, [Access: 20.01.2021].
• How do Bitcoin Transactions Work. http://www.coindesk.com/information/how-do-bitcoin-transactions-work/,[Access: 11.02.2015].
• How does Bitcoin work, https://bitcoin.org/en/how-it-works, [Access: 20.01.2021].
• Knight shows how to lose 440 million in 30 minutes, http://www.bloomberg.com/bw/articles/2012-08-02/knight-shows-how-to-lose-440-million-in-30-minutes, [Access: 20.01.2021].
• Mining hardware comparison, https://litecoin.info/Mining_hardware_comparison, [Access: 20.01.2021].
• NBP: Report on Poland's full participation in the third stage of the Economic and Monetary Union, http://www.nbp.pl/Publikacje/O_Euro/RE1.pdf, [Access: 20.08.2020].
• NUMTECH: GPGPU and financial business, http://www.numtech.co.jp/files/documents/seminar/20101019/20101019E.pdf, [Access: 20.01.2021].
• NVIDIA: Computational Finance, http://www.nvidia.com/object/computational_finance.html, [Access: 20.01.2021].
• Bitcoin specification, http://nakamotoinstitute.org/bitcoin/, [Access: 20.01.2021].
• TOP 500 The List, http://www.top500.org/, [Access: 20.01.2021]

Identifiers

DOI

10.23830/16/II/2019/5788