Hyperparameter-Based Feature Selection for Breast Cancer Data Analysis

A crucial strategy for analysing various datasets with machine learning models is feature selection. Although machine learning techniques have been applied to multiple datasets, a few classical techniques have been shown to perform less well on particular datasets than current scenario approaches. As a result, it must perform better by tuning or hyperparameter-based models, which is a difficult task to evaluate. Therefore, we have suggested tuning and neural network-based models to enhance performance during model demonstration on a specific dataset. Our proposed model for feature selection is evaluated using a variety of machine learning classifiers, including Support Vector Machines (SVM) (using Radial Basis Function (RBF)), K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Artificial Neural Networks (ANN). The model is demonstrated using the techniques above and the breast cancer dataset. It performed well when using the tuning SVM approach (99 %) compared to other methods, which had the lowest accuracy performance at GNB (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 5 \%}$</tex>).