ENHANCING MODEL ACCURACY USING FEATURE SELECTION TECHNIQUE

Abstract

For feature selection, it is necessary to choose a subset of the most important characteristics that produces the same outcomes as the entire set of data. It is possible to evaluate the effectiveness and efficiency of a feature selection approach. Efficiency is the amount of time it takes to find a subset of characteristics, whereas effectiveness is the caliber of the subset. Based on these variables, this study suggests and evaluates a feature selection method called clustering. There are two components to the Clustering Based Feature Selection technique Initially, graph-theoretic clustering methods are employed to divide features into groups. The Clustering Based Feature Selection clustering-based approach is anticipated to produce a subset of useful and independent features since the attributes in separate clusters are often independent.