Accuracy analysis comparison of random forest over support vector machine in predicting bankruptcy

• Main Authors: Ali, Mohammed Mustafa, Babu, R. Samuel Rajesh
• Format: Conference Proceeding
• Language: English
• Subjects: Accuracy; Algorithms; Bankruptcy; Statistical analysis; Support vector machines
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0234069

The objective of this research is to develop a sophisticated method for predicting bankruptcy that makes use of support vector machines (SVM) rather than random forests and produces more accurate results. The Constituents and the Methods involved: In the case of group 2, which is sometimes referred to as Random Forest, the sample size includes twenty individuals. Support vector machines are utilised in order to facilitate the classification process (SVM). A check with one tail is carried out with a Confidential Interval (CI) of 95, and the price of importance is set at beta 1.00. In the support vector machine (SVM), the alpha price is believed to be 0.8, and the G-Power price is likewise considered to be 0.8. The results showed that the SVM algorithm acquired an accuracy rate of 97.3 percent, while the Random Forest community Algorithm achieved a recognition rate of 98.8 percent. This was determined after all of the assessments that were carried out inside the research were conducted and completed. As a result of the fact that the mean accuracy detection is 1.483 (±2SD) and the significance value is 0.00 (p