Bankruptcy Study Using Artificial Intelligence

Abstract

Bankruptcy is a legal process that declares the debtor's inability to repay the debt and a subsequent chain of repayments to the creditor. Preventing the risk of company failure, or a long time, it has been a subject that the academic and industrial circles attach great importance to, once there are any errors in prediction and judgment, the market will have a serious impact. This study uses data samples obtained from the Indian Engineering School and Pondicherry University at UCI Data Bank. Build an AI prediction model with python, the modeling method includes Decision tree, Logistic Regression (LR), (DT), and Support Vector Machine (SVM). The results of this study show that the accuracy of LR, DT and five SVM models are 0.56, 1.0, 0.54 (linear), 0.96 (polynomial), 1.00 (Gaussian), 0.54 (Sigmoid). The results show that Support Vector Machine (Radioactive) models and Decision Trees perform best.