Agricultural and Biological Research

Using rotation forest and support vector machine algorithms for predicting cancer risk analysis

Balasaheb Tarle*, Vaishali Tidake, Sopan Talekar and Poonam Chaudhari

Cancer is a leading cause of cancer-related deaths affecting millions worldwide. Early detection and accurate diagnosis of cancer can significantly improve survival rates. Machine learning algorithms have shown great potential in predicting cancer risk analysis. In this research paper, we compare the performance of two popular algorithms, the Rotation Forest Algorithm and the Support Vector Machine Algorithm, for predicting cancer risk analysis. The datasets used for this study are from the UCI Machine Learning Repository. We randomly split each dataset into training and testing sets and evaluated the algorithms' performance using accuracy, precision, recall, specificity, and F1 score. Our results showed that the Rotation Forest better performed SVM on most datasets. The average enhancement is around 4.67%. It is observed that the RF approach also enhances classification performance. Using hypothesis tests, such as the Wilcoxon rank sum test and t-test, it was determined that the alternative hypothesis was true.