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

Fig. 2: Clustering result (non-bankrupt company 2) The member features of Cluster 1, to which Company 1 belongs, are illustrated in Figure 3. On the horizontal axis, non-bankrupt companies are arranged toward the left, and bankrupt companies are arranged toward the right. The vertical axis represents the group mean value of the maximum change rate of the negative absolute values. Whereas the bankrupt companies in Cluster 1 are characterized by an outstanding change rate for investing cash flow (investment_cash_ flow_dmax), the ratio of bankrupt companies is the lowest of the four clusters, which leads to an interpretation that non-bankrupt company 1 has little risk of bankruptcy. Fig. 3: Member features of Cluster 1 Figure 4 shows the member features of Cluster 3, where non-bankrupt Company 2 belongs. The markedly high contributing factor of the bankrupt company group in Cluster 3 is the return on equity (return_on_equity_dmax), followed by the investing cash flow (investment_cash_flow_dmax). Given that the ratio of bankrupt companies in this cluster is 78%, as indicated in Table 6, it is interpreted that Company 2 can be at risk of bankruptcy if its return on equity and investment in cash flow decline, suggesting the need to consider countermeasures in relation to these factors. 15 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