<![CDATA[The skin is the largest outer part of the human body. Maintaining skin is very important. The appearance of unusual things on the skin will raise concerns because it is possible that the skin could be affected by fatal diseases. Limited specialist doctor examinations in Indonesia add to the difficulty in preventing skin diseases. Therefore, this research was conducted to facilitate the classification of skin diseases. Skin disease classification must have good accuracy or precision in classifying each type. This study classifies skin diseases accurately and precisely by evaluating the performance of Oversampling and Augmentation techniques. This research uses the Convolutional Neural Network (CNN) approach. Using the HAM10000 dataset which contains dermoscopic images with a total of 10015 images. This study applies Oversampling to overcome data imbalance and applies image augmentation to improve model training performance. The performance of the model is evaluated using accuracy, recall, precision, f1-score, specificity, sensitivity, gmean. Comparisons are obtained from testing the original dataset, the dataset with oversampling and various augmentation techniques. The evaluation results show that the third test, namely classification using the CNN approach with oversampling and augmentation rotation, zoom, width, height, vertical_flip, gets the best results, namely accuracy 0.98, recall 0.98, precision 0.98, f1-score 0.98, specificity 0.99, sensitivity 0.98, gmean 0.98.]]>
