Performance Accuration Method of Machine Learning for Diabetes Prediction

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning (ML) techniques allow us to obtain predictively, the dataset we are testing is pima-indian-diabetes with a dataset of 765 raw data with 8 data features and 1 data label we developed a method to achieve the best accuracy from the 5 methods we use with the stages of separation training and testing the dataset, scaling features, parameters evaluation, confusion matrix and we get the accuracy of each method, and the results of the accuracy we get with these 5 methods Gradient-boosting is best with an accuracy score of 0.8, Decision Tree 0.72, Random Forest 0.72, next is Logistic Regression 0.7, and then followed by K-NN method with a score of 0.65.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.