Evaluating Machine Learning Models for Gender Detection Using Palm Images: A Comparative Approach

Abstract

This study examines how machine learning can identify a person's gender based on palm images. It compares two widely used models, Random Forest and Gradient Boosting, to evaluate their effectiveness. The dataset, obtained from Kaggle, was selected for its reliability and diversity. The research goes through essential steps like data preparation, feature selection, model optimization, and performance comparison. It also highlights the advantages and limitations of each model, offering valuable insights for those interested in this field.