BREAST CANCER

Breast cancer remains a significant health concern worldwide, necessitating the development of accurate and reliable diagnostic models. This project aims to construct an ensemble model utilizing the Wisconsin Breast Cancer dataset, which has been preprocessed using correlation coefficient and ReliefF feature selection techniques. The dataset is subsequently trained using three popular classifiers: Support Vector Machine (SVM), Naive Bayes, and Logistic Regression. The results demonstrate that the proposed ensemble model leveraging SVM, Naive Bayes, and Logistic Regression classifiers, along with voting, bagging, and stacking techniques, yields superior performance with 96% accuracy compared to individual classifiers and existing benchmark models. This project contributes to the field of breast cancer diagnosis by providing an effective and reliable ensemble model that can assist
medical professionals in making accurate and timely predictions for breast cancer classification.