In today’s world using data mining and classification is considered to be one of the most important techniques, as today’s world is full of data that is generated by various sources. However, extracting useful knowledge out of this data is the real challenge, and this paper conquers this challenge by using machine learning algorithms to use data for classifiers to draw meaningful results. The aim of this research paper is to design a model to detect diabetes in patients with high accuracy. Therefore, this research paper using five different algorithms for different machine learning classification includes, Decision Tree, Support Vector Machine (SVM), Random Forest, Naive Bayes, and K- Nearest Neighbor (K-NN), the purpose of this approach is to predict diabetes at an early stage. Finally, we have compared the performance of these algorithms, concluding that K-NN algorithm is a better accuracy (81.16%), followed by the Naive Bayes algorithm (76.06%).