OPTIMIZATION OF PARAMETERS K IN THE K-NEAREST NEIGHBOUR ALGORITHM FOR CLASSIFICATION OF DIABETES DISEASE BASED ON PYTHON

Abstract

Diabetes doesn't just cause premature death worldwide. This disease is also a major cause of blindness,
heart disease, and kidney failure. The International Diabetes Federation (IDF) organization estimates
that at least 463 million people aged 20-79 years in the world have diabetes in 2019, or the equivalent of
a prevalence rate of 9.3% of the total population at the same age. The research objective is to optimize
the k parameter in the k-NN algorithm for python-based diabetes classification. This research was
conducted using the experimental method. This experimental method was carried out by researchers by
changing the k parameter with a value of 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31, 33, 35, 37,
39, 41, 43, 45, 47, and 49 and getting the research results for optimizing the value of k = 11 having the
highest accuracy of 0.9617.