Breast cancer poses a serious threat in several developed as well as developing countries like Nigeria. The use of machine learning and data mining techniques has revolutionized the whole process of predicting the presence of breast cancer. In this work, we evaluate and investigate three selected classification algorithms using Waikato Environment for Knowledge Analysis (WEKA for short). WEKA is an open source data mining software mainly used for academic and research purpose. The algorithms tested are C4.5, multi-layer perceptron and Naive Bayes. Experimental results show that C4.5 proves to be the best algorithm with highest accuracy.