The project entitled “DIABETES PREDICTION USING MACHINE LEARNING” is based on Data analytics. Diabetes is a long-standing disease with the likely to cause a global health care crisis. As per International Diabetes Federation (IDF), 382000 thousand people are living with diabetes over the entire world. After a decade, this will be doubled as 592000 thousand. Diabetes is caused due to the acceleration of blood glucose. The higher levels of sugar produce the sign of frequent urination, high levels of thirst and hunger. Diabetes is one of the main causes of myopia, kidney failure, amputations, heart failure and stroke. When we eat food, our body turns it into sucrose, or glucose. At that point, our pancreas is about to release insulin. Insulin serves as a manager to open our cells and to allow the glucose to enter and permit us to use the glucose for energy. However, with diabetes, this procedure will not be completed. Type 1 and type 2 diabetes are the most common forms of the disorder, but there are also other types, such as gestational diabetes, which occurs during gestation, as well as other forms. Machine learning is a booming scientific technology in data science dealing with the ways in which machines understands from experience. The goal of this project is to build a system, which can do early prediction of diabetes for a patient with a higher level of accuracy by combining the results of various machine-learning aspects. The algorithms like K-means algorithm, Random Forest, Logistic Regression, Support Vector Machine and Decision tree are used in this project. The correctness of the model based on algorithms is calculated and the unique model is taken for prediction of diabetes.