To avoid diseases, early disease prediction is crucial in the medical industry. One of the most hazardous diseases in the world is diabetes. Our dietary habits in modern lifestyles are often high in sugar and fat, which has raised the risk of diabetes. Understanding the disease's symptoms is crucial for making predictions about it. Machine-learning (ML) techniques are useful right now for identifying diseases. To anticipate and analyse in this case, we employed the support vector machine and the k-nearest neighbour technique. These models examine the data set to evaluate whether a positive or negative diabetes diagnosis has been made.