Cancer is among the most prevalent causes of mortality worldwide. Breast cancer is one of most often diagnosed cancers, with over 200 different varieties to choose from. Given the high prevalence of morbidity and death, early and accurate diagnosis are critical. For this purpose, symptoms must be carefully assessed and classified and this can be done by ML and DL techniques. The main goal of this research is to examine several ML and DL approaches for breast cancer diagnosis and accuracy prediction. The primary dataset being used for research purposes is the WBCD. The following are the findings of the algorithms used: 93.08 percent accuracy for LR, 93.61 percent accuracy for KNN, 96.50 percent accuracy for SVM, and 95.10 percent accuracy for Multilayer Perceptron.