Data scaling performance on various machine learning algorithms to identify abalone sex

This study aims to analyze the performance of machine learning algorithms with data scaling process show method's effectiveness. It uses min-max (normalization) and zero-mean (standardization) techniques in abalone dataset. The stages carried out this included normalization on physical measurement features. model evaluation was using k-fold cross-validation number 10. Abalone datasets were normalized algorithms: Random Forest, Naïve Bayesian, Decision Tree, SVM (RBF kernels linear kernels). eight features dataset that did not too influence scaling. There is an increase SVM, while Forest decreases when applied has highest average balanced accuracy (74.87%) without