A Comprehensive AutoML-based Analysis of Machine Learning Algorithms for Breast Cancer Prediction Comparative Performance and Insights

Breast cancer accounts for one of the foremost percentages of mortality among females worldwide. Early detection of the disease is critical in raising the chance of survival and reducing the intensity of treatment. This research incorporates machine learning methods, which include XGBoost, Random Forest, Stacked Ensemble, Gradient Boosting Machine (GBM), and Support Vector Machine (SVM), in order to predict breast cancer among patients. Results indicate that the XGBoost was the best model with maximum accuracy of 0.865235. The Stacked Ensemble model performed well with an Acuraccy of 0.863938 and accuracy of 86.5%. The ensemble methods play a vital role in the prediction accuracy which boost the possibility of diagnosis at an earlier stage of breast cancer.