• Nahid Noor Hussan
• Prof. Suresh. S. Gawande

Changing the info information into the arrangement of highlights is called include extraction if the highlights extricated are precisely picked it is normal that the highlights set will separate the pertinent data from the information so as to play out the coveted errand utilizing this diminished portrayal rather than the full size info. In this paper, gradient boosting machine learning technique to train the Diagnosis diabetes to classify the diabetes patients is two class values. The positive diabetes patients are defined by class ‘0’ value and negative diabetes patients are defined by class ‘1’. The total Diagnosis diabetes dataset is 768. All dataset applied to the gradient boosting machine learning technique and get the 500 dataset is not diabetes and 268 dataset is diabetes. In proposed algorithm we used an ensemble of gradient boosting to achieve an accuracy of 81.95%. The Majority vote-based model as demonstrated which comprises of Naïve Bayes, Decision Tree and Support Vector Machine classifiers gave an accuracy of 76.56%, sensitivity of 79.16% and specificity of 77.476% for diabetes disease dataset.

Diabetic dataset, Classification, Machine Learning, Gradient Boosting

"Optimization Accuracy of Diabetes Prediction using Different Machine Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.a39-a43, March-2023, Available :http://www.jetir.org/papers/JETIR2303006.pdf

"Optimization Accuracy of Diabetes Prediction using Different Machine Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppa39-a43, March-2023, Available at : http://www.jetir.org/papers/JETIR2303006.pdf