Review of Literature on Improving the KNN Algorithm

Abstract

K-Nearest Neighbors (KNN) is a classification algorithm that has been widely used in the world of machine learning. The KNN algorithm classifies objects with learning data that are closest to the object. The special case where the classification is predicted based on the closest learning data is called the Nearest Neighbors algorithm. Classification is an important issue in processing big data, data science, and machine learning. KNN is one of the oldest, simplest, and also accurate algorithms for pattern classification and regression models. Many researchers have also improvised KNNs and the results obtained by these studies have changed a lot in terms of the accuracy of the results. The purpose of this paper is to see the improvement of several types of development of the KNN algorithm.