Early warning systems against bankruptcy risk and NLP: can ChatGPT predict corporate distress?

• Autorzy: Siciński Jędrzej

Identyfikatory

DOI

10.29119/1641-3466.2023.170.28

• Języki publikacji: EN

Abstrakty

EN

Purpose: The main purpose of this paper is to evaluate the effectiveness and usability of one of the more groundbreaking and more widely commented NLP-technique-employing inventions, i.e., the ChatGPT application acting as a digital advisor in the field of counterparty financial standing and bankruptcy risk assessment. Design/methodology/approach: The algorithmic potential presented by the ChatGPT tool can be a valuable solution in supporting the manager's work. In this study, the current potential of this solution in supporting financial analysis, and in particular, bankruptcy risk assessment, was checked. The study was carried out using the following methods: analysis and synthesis (1.), critical analysis of the literature (2.), and an experiment involving the use of a natural language processing application (3.). Findings: In the course of the research, it was found that the ChatGPT tool, according to the current state of knowledge, has extensive usability and is able to conduct interactions that in many cases are similar to communication with a human being. The tested language model shows a much higher level of training on general data than in solving narrow problems in specific fields. Nevertheless, its development potential should be assessed highly and probably its adaptation to solve highly specialized tasks in management will not be a long-term process, which makes it a candidate for the role of a digital managerial advisor in the future. Research limitations/implications: The first stage of the research covered only solving problems with the use of the simplest algorithms, such as discriminant analysis (MDA) and the study of entities whose financial statements are widely available on the web, which was a relatively low level of complexity for the language model. Practical implications: The research results are a signal that digitization and the digital revolution are not just theoretical slogans, but real functioning technologies that can change the nature of the manager's work (and the entire management system) in the near future. The development potential of NLP technology in management, which was confirmed in this work, suggests that an appropriate strategy for implementing these technologies is needed today. Originality/value: In this study, one of the first attempts was made to assess the potential and adaptability of natural language processing systems to support a manager in assessing the financial condition and risk of bankruptcy of entities.

Słowa kluczowe

EN

early warning systems against bankruptcy; insolvency; artificial intelligence; natural language processing; chatGPT

PL

systemy wczesnego ostrzegania przed upadłością; niewypłacalność; sztuczna inteligencja; przetwarzanie języka naturalnego; chatGPT

• Wydawca: Wydawnictwo Politechniki Śląskiej
• Czasopismo: Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska
• Rocznik: 2023
• Tom: z. 170
• Strony: 439--455
• Opis fizyczny: Bibliogr. 28 poz.

Twórcy

autor

Siciński Jędrzej

• University of Gdańsk, Faculty of Management, Department of Strategic Development; Sopot

• https://orcid.org/0000-0001-6810-3792

Bibliografia

• 1. Alaka, H.A., Oyedele, L.O., Owolabi, H.A., Kumar, V., Ajayi, S.O., Akinade, O.O., Bilal, M. (2018). Systematic review of bankruptcy prediction models: Towards a framework for Tool Selection. Expert Systems with Applications, 94, pp. 164-184. https://doi.org/10.1016/ j.eswa.2017.10.040
• 2. Altman, E.I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, 23(4), pp. 589-609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x.
• 3. Antonowicz, P. (2007). Metody oceny i prognoza kondycji ekonomiczno finansowej przedsiębiorstw. Gdańsk: Wydawnictwo ODiDK.
• 4. Antonowicz, P. (2011). Długość cyklu inkasa należności i rotacji zapasów w przedsiębiorstwach na trzy lata przed sądowym ogłoszeniem upadłości. Problemy Zarządzania, no. 1(31), pp. 53-71
• 5. Aslam, F., Hunjra, A.I., Ftiti, Z., Louhichi, W., Shams, T. (2022). Insurance fraud detection: Evidence from Artificial Intelligence and machine learning. Research in International Business and Finance, 62, 101744. https://doi.org/10.1016/j.ribaf.2022.101744
• 6. Bloomberg (2023). CFOs Will Get Their Own AI Chatbot as Part of Brex Project. Retrieved from: https://www.bloomberg.com/news/articles/2023-03-07/brex-to-offer-chatgpt-style-openai-chatbot-for-cfos-finance-professionals#xj4y7vzkg?leadSource=uverify%20wall, 09.03.2023.
• 7. Forsal (2019). Pasterz robotów i manager śmierci cyfrowej. W ciągu 10 lat powstaną zupełnie nowe zawody. Retrieved from: https://forsal.pl/artykuly/1410248,praca-przyszlosci-w-ciagu-10-lat-powstana-zupelnie-nowe-zawody.html, 07.03.2023
• 8. GOV.PL (2020). Test Turinga i sztuczna inteligencja. Retrieved from: https://www.gov.pl/ web/ncbr/sztuczna-inteligencja--czy-pamietamy-o-tescie-turinga, 27.02.2023.
• 9. IBM (2023). Natural language processing. Retrieved from: https://www.ibm.com/topics/ natural-language-processing, 27.02.2023.
• 10. Khurana, D., Koli, A., Khatter, K., Singh, S. (2022). Natural language processing: state of the art, current trends and challenges. Multimedia Tools and Applications, 82(3), 3713-3744. https://doi.org/10.1007/s11042-022-13428-4.
• 11. Kitowski, J. (2021). Modele dyskryminacyjne jako instrument oceny zagrożenia upadłością przedsiębiorstw. Nierówności Społeczne a Wzrost Gospodarczy, 68(4), 145-160. https://doi.org/10.15584/nsawg.2021.4.8.
• 12. Kowalak, R. (2017). Rola systemów wczesnego ostrzegania w procesie podejmowania decyzji o restrukturyzacji przedsiębiorstwa. Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu, no. 470, p. 159.
• 13. Liddy, E.D. (2001). Natural Language Processing. Encyclopedia of Library and Information Science, 2nd Ed. NY. Marcel Decker, Inc. p. 2.
• 14. Maciąg, R. (2022). Zaawansowane procedury NLP jako przesłanka rekonstrukcji idei wiedzy. Zarządzanie w Kulturze, 23(1), pp. 37-53.
• 15. Migdał-Najman, K., Najman, K. (2018). Dirty data – profiling, cleansing and prevention. Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu, 508, 146-156. https://doi.org/10.15611/pn.2018.508.15.
• 16. Moser, E. (2021). Against robot taxes: scrutinizing the moral reasons for the preservation of work. AI And Ethics, 1(4), 491-499. https://doi.org/10.1007/s43681-021-00062-3.
• 17. MPost (2023). Chaptgpt passes the turing test. Retrieved from: https://mpost.io/chatgpt-passes-the-turing-test/, 27.02.2023.
• 18. Osika, G. (2021). Dilemmas of social life algorithmization - technological proof of equity. Scientific Papers of Silesian University of Technology Organization and Management Series, 151. https://doi.org/10.29119/1641-3466.2021.151.36.
• 19. Paprocki, W. (2017). Perspektywy zastosowania sztucznej inteligencji w systemach obsługi mobilności - przykład organizacji pasażerskich przewozów lotniczych. Research Journal of the University of Gdańsk. Transport Economics and Logistics, vol. 74, pp. 341-355.
• 20. Pociecha, J., Pawełek, B., Baryła, M., Augustyn, S. (2014). Statystyczne metody prognozowania bankructwa w zmieniającej się koniunkturze gospodarczej. Kraków: Fundacja Uniwersytetu Ekonomicznego w Krakowie, p. 8.
• 21. Shetty, S., Musa, M., Brédart, X. (2022). Bankruptcy Prediction Using Machine Learning Techniques. Journal of Risk and Financial Management, 15(1), 35. https://doi.org/10.3390/ jrfm15010035.
• 22. Siciński, J. (2021). System wczesnego ostrzegania przedsiębiorstw przed ryzykiem upadłości na przykładzie branży transportowej. Sopot: Centrum Myśli Strategicznych, pp. 8-10.
• 23. Sira, M. (2022). Artificial Intelligence and its application in Business Management. Scientific Papers of Silesian University of Technology. Organization and Management Series, 165, 307-346. https://doi.org/10.29119/1641-3466.2022.165.23.
• 24. Sliż, P. (2019). Robotization of business processes and the future of the labor market in Poland–preliminary research. Organizacja i Kierowanie, 185(2), p. 67-79.
• 25. Tamkin, A., Brundage, M., Clark, J., Ganguli, D. (2021). Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models, ArXiv:2102.02503. Retrieved from: https://arxiv.org/abs/2102.02503v1, 27.02.2023.
• 26. Turing, A.M. (1950). Computing Machinery and Intelligence. Mind, 236(14), 433-460.
• 27. WEF (2023). How does chagpt differ from intelligence. Retrieved from: https://www.weforum.org/agenda/2023/02/how-does-chatgpt-differ-fromhuman-intelligence?utm_source=facebook&utm_medium=social_scheduler&utm_term=Artificial+Intelligence&utm_content=28%2F02%2F2023+20%3A40, 7.03.2023.
• 28. Zięba, M., Tomczak, S.K., Tomczak, J.M. (2016). Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction. Expert Systems With Applications, 58, 93-101. https://doi.org/10.1016/j.eswa.2016.04.001.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).