• Akshita Goel
• Prof. (Dr.) ML Sharma
• Prof. Sunil Maggu
• Deepali Guleria
• Srishti Bansal

Data mining is use to extract those patterns that were previously hidden and unknown. One of the tasks of data mining is Classification. Health care data is often large, diverse and multiplex because different variable types are present. These days, it is necessary to get knowledge from such data. Data mining is utilized to extract knowledge by constructing models from healthcare data such as sugar patient sets. Diabetes is a very serious disease and it is a major health challenge worldwide. Using data mining methods for early prediction of diabetes has gained major popularity. In this paper, we are going to predict whether a person is diabetic or not using data mining. K-Nearest Neighbour algorithm is used for diabetes data and classification. We have compared the accuracy for classifying the data.

Data mining, K-Nearest Neighbour , K-NN, Diabetes, prediction, Bagging and boosting, accuracy, error rate.

"Diabetes prediction using data mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.7-13, April-2019, Available :http://www.jetir.org/papers/JETIR1904803.pdf

"Diabetes prediction using data mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp7-13, April-2019, Available at : http://www.jetir.org/papers/JETIR1904803.pdf