The early detection and accurate classification of skin cancer, particularly melanoma, is crucial for effective treatment and patient survival. This systematic review evaluates the current state of machine learning (ML) techniques applied to the classification of skin cancer images. The review covers various ML approaches, including convolutional neural networks (CNNs), support vector machines (SVMs), and deep learning methods, emphasizing their advantages, limitations, and diagnostic accuracy. Additionally, the databases used, image preprocessing methods, and evaluation metrics are discussed. Findings highlight the necessity to improve model generalization and address challenges related to image quality and diversity. Future research areas are identified to enhance the clinical implementation of these techniques, aiming for more effective and accessible skin cancer diagnosis.