Skin cancer is one of the most commonly diagnosed types of cancer in the world with a high rate of mortality. The high mortality rate is usually caused by late treatment. An early diagnosis and treatment will significantly improve the recovery rate. Unfortunately, access to dermatologist treatment is limited due to factors such as time, cost, access, and knowledge regarding the skin cancer risk. Based on these problems, a model that can diagnose three types of skin cancer by analyzing images of skin cancer is developed. This research uses the Convolutional Neural Network algorithm to classify and predict skin cancer type and its probability result. The developed model will then be used as the backbone for a web-based system to predict types of skin cancer. The developed system can accept input directly from the camera of a device or accept image file upload before performing the analysis and classification and displaying the skin cancer types and probabilities to the user. The developed system can act as people’s first action to diagnose skin cancer, before going to a dermatologist for further diagnoses and treatment.