Cancer in breast is a frequently occurring type of cancer that impacts individuals globally and can be fatal if not detected and treated in a timely manner. Depending on the tools, datasets, and conditions, researchers have investigated a variety of strategies, including ML techniques , DL methods, and data mining techniques, to predict breast cancer with variable degrees of accuracy. The main aim of this study is to analyze and distinguish the existing machine learning and data mining techniques to determine the most effective way for correctly predict breast cancer utilizing large datasets. The main objective is to give newcomers helpful knowledge on understanding machine learning algorithms and laying the groundwork for deep learning. This study looked at several studies that show the usefulness of DL and ML algorithms in detecting breast cancer across multiple datasets. SVM, KNN, RF, ANN, and CNN were discovered to have the highest accuracy rates among the algorithms. Future study will focus that allows users to calculate their risk of developing breast cancer.

Breast cancer, prediction, diagnosis, deep learning algorithm, machine learning algorithm.