The second greatest cause of death for women worldwide is breast cancer. When abnormal cells in the body proliferate out of control, cancer is the result. The diagnosis of breast cancer was established using anthropometric data obtained from standard blood tests. From the UCI Machine Learning Repository, the Breast Cancer Coimbra Data Set was obtained and put to use. One popular classification decision tree method is the C4.5 approach. By selecting the appropriate features and applying the appropriate strategy to address class imbalance throughout the classification process, the performance of the C4.5 algorithm may be enhanced. To determine the accuracy of the classification, tests are conducted using a confusion matrix. Accuracy in this study is anticipated to increase with the application of the C4.5 Algorithm, the Bagging approach to address class imbalance, and the PSO feature selection method. The C4.5 Algorithm, PSO, Bagging Technique produce the best accuracy results, with an average of 86.36 percent. The C4.5 classification method has the second highest accuracy, with a PSO accuracy of 79.39 percent. Utilizing the Bagging Technique in conjunction with the C4.5 Algorithm, the accuracy of 75.0% is the third highest. Furthermore, it has a 65.71 percent accuracy with the C4.5 categorization. As a result, the increase in accuracy from before adding PSO and Bagging Technique was 20.65%, indicating that the inclusion of PSO and Bagging Technique had a substantial impact on the calculation process.