Global Journal of Management and Business Research, A: Administration and Management, Volume 22 Issue 1

Fig. 4: Member features of Cluster 3 V. C onclusion By extracting feature values from chronologically ordered financial data used in machine learning, this study sought to develop a prediction model that not only predicts a bankruptcy during a binary judgment, but can also identify the financial variables that are likely to drive a company into bankruptcy. The evaluation test using sample data was successful in that the model clustered bankrupt companies according to the explanatory factors for their bankruptcy. Non-bankrupt companies were also grouped into clusters with the corresponding risk factors of bankruptcy. Thus, the study demonstrated that this model of cluster analysis, based on feature values taken from time-series financial statement data, is effective in predicting and identifying risks of future bankruptcy. A cknowledgment This study was funded by the Japanese Ministry of Education, Culture, Sports, Science, and Technology (MEXT) through a Grant-in-Aid for Scientific Research (KAKENHI), No. 19K01843. R eferences R éférences R eferencias 1. SeigoTasaka. Empirical study about a bankruptcy company: It is based on the model of Beaver and Altman [in Japanese], KwanseiGakuin University NII-Electronic Library Service, pp. 71-99. 2. Yosuke Kono and Masahiko Murata. Discussion on the possibility of predicting corporate bankruptcy [in Japanese], Momoyama Gakuin University Gakusei Ronshu, Reissue No. 24, 2009. 3. Ayaka Okubo. Study on Black-in Bankruptcy Mechanism through Financial Statements focused on Cash Flow [in Japanese], Junior College of the University of Aizu Research Dissertation Papers for Year 2010, 2010. 4. Masaru Ishikawa and Ngai Chung Sze. A Study of Corporate Bankruptcies Based on the Cash Flow Information [in Japanese], Toyo Gakuen University Business and Economic Review Vol. 3(1), pp. 35-58, 2012. 5. Ryuji Mizoguchi and Shunsuke Nakajima. Discriminant analysis of companies and bankruptcy probability estimation [in Japanese], Nanzan University Department of Information Engineering and Science 2012 Dissertations (Abstracts), 2012. 6. Jiang Feihong. Financial Forecast and Cash Flow Information [in Japanese], Meiji University Studies in Business Administration, No. 19, pp. 175-192, 2003. 7. Koji Jidaisho, Hamido Fujita, Masaki Kurematsu, and Jun Hakura. Experiment of Risk Prediction on Japanese Companies Using a Bankruptcy Risk Prediction Model [in Japanese], Iwate Prefectural University Faculty of Software and Information Science Dissertations, 2017. 8. Yuichi Masuyama.The Conditions for Corporate Growth in the Context of Corporate Bankruptcy Analysis [in Japanese], HikoneRonso Online Journal (Shiga University Economic Journal), No. 413, pp. 16-31, 2017. 9. Yasuhiro Saigo and Kazutoyo Nakano. A Basic Study on the Cash Flow Accounting Information and Valuation [in Japanese], Bulletin of Toyohashi Sozo University, No. 16, pp. 25-43, 2012. 10. Teikoku Databank. https://www.tdb.co.jp/tosan/ teigi.html (accessed on July 22, 2019). 11. Delisting website. http://delisting.info/index.html (accessed on Oct. 17, 2019). 12. Kabunushi Pro website. http://www.kabupro. jp/code/9963.htm (accessed on Oct. 17, 2019). 16 Global Journal of Management and Business Research Volume XXII Issue I Version I Year 2022 ( ) A © 2022 Global Journals A Study on Machine Learning Prediction Model for Company Bankruptcy using Features in Time Series Financial Data