The data set (pima-indians-diabetes.data) is data from the US Centers for Disease Control and Prevention. The background is to record diabetes symptom information in the United States. Now 1/7 adults in the United States suffer from diabetes. But by 2050, this proportion will grow rapidly to as high as a third. Diabetes can be predicted by using a data set about Indian diabetes from the UCI machine learning database and related algorithms through data mining. This problem is essentially a binary classification problem.