Breast Carcinoma Prediction: A Comparative Analysis on WDBC Dataset Using Classification Techniques

Researchers are currently accomplished with machine learning algorithms developing prediction models and categorizing data across various fields particularly in medical field. Where ML algorithms gives best diagnosis and evaluate to make better decision. presently, the most frequent malignancy in women is Breast Carcinoma and death percentage also increased extremely because of Breast Carcinoma. BC is representing 11.7% of all cancer cases and mortality rate is almost 50%. Using ML algorithms doctors can accurate diagnosis of BC in early stages. SVM outperformed the other two classifiers, achieving the highest accuracy rate of 96%. In this paper, we compared three machine learning algorithms: K-NN, SVM, and Naïve Bayes. We did this by using the WDBC dataset and analysing the confusion matrix to improve accuracy, precision, recall, and F1-score. The Python programming language and the Scikit-learn library were used to carry out the work in the Anaconda environment.