Extension of Breast Cancer Prediction Model using Random Forest

Breast cancer early detection can save lives, but accurate diagnosis remains challenging. Previous work showed that Support Vector Machine (SVM) outperformed a Decision Tree classifier (91.92% vs. 87.12% accuracy). This study extends the work by introducing a Random Forest classifier using the same dataset, preprocessing, and a 75–25 train-test split. Hyperparameter tuning, balanced class weights, and 5-fold cross-validation were applied.