Breast Cancer Prediction with Gradient Boost and XGBoost

In the arena of cancer research, it has been able to discover cancer patients utilizing genetic factor information grouped together with artificial intelligence innovations. To strengthen the foretelling paradigms, it is essential to integrate biological, social, and demographic data. In our research article, the gradient boost technique, the (SVM) support vector machine classier, the (LR) logistic regression technique, random forest, the (DT) decision tree classifier, k nearest neighbour, XGBoost, and adaptive linear neuron classifiers have been separately evaluated. In the suggested model, primary objective is to choose the most suitable features. By using correlation matrix and principal component analysis (PCA), we scaled down features for the better enhancement of the model’s efficacy. It gave us 10 important features from the dataset. We have successfully achieved 100% accuracy in the prediction through gradient boost and XGBoost classifier with a 97.50% cross-validation score.