Comparative Performance Analysis of machine learning models for Breast Cancer Prediction

Recently, large-scale data merging and ensemble learning algorithms have emerged as promising approaches to breast cancer prediction and classification. Computer-aided detection and diagnosis technology can help people live longer by facilitating early detection of breast cancer. Aberrant cell division in the breast is the primary cause of breast cancer, which can develop into either a benign or malignant tumor. Because of this, early detection of breast cancer is essential, and many lives can be spared with effective treatment. The results and assessments of several machine learning models for detecting breast cancer are covered in this study. The approach was developed using the Wisconsin Breast Cancer Diagnostic (WBCD) dataset. The dataset has some intriguing data even though it is small. The data was examined and utilized in several machine learning models. Support Vector Machine (SVM), K-Neighbors Classifier (KNN), Naïve Bias model, Logistic Regression (LR), AdoBoost and Decision Tree (DT) were used for prediction. It is discovered that the AdoBoost model produces the best results when the results are compared. $96 \%$ accuracy and logistic regression model is predicted $96 \%$ of ROC value. Logistic regression model and AdoBoost, which is better than the previously published approach.