A Performance Comparison of Kernel SVM with Tuned Hyperparameter GridSearchCV Algorithm using Machine Learning Techniques for Child Immunization

Abstract

To design a model for the diagnosis of Child Immunization that will be used to predict, analyse, monitor, and forecast the performance measure in the field of Child Immunization in an optimal period, identify the severity of the child growth. In this research, we have used the Child Immunization dataset and using classification model kernel SVM and GridSearchCV Hyperparameter algorithms or applying confusion matrix for accuracy. In this research based on our dataset, in Kernel SVM, we have got 75% accuracy and our Hyperparameter algorithm GridSearchCV, we have received 77% accuracy. In this research, we have concluded that with two algorithms Kernel SVM and GridSearchCV, our approach of hyper tuning parameters of GridSearchCV algorithm produced results better than Kernel SVM with our child immunization dataset.