The study’s primary purpose is to propose an automatic melanoma cancer detection system using Random Forest Algorithm and Convolutional Neural Network algorithm (CNN) to detect melanoma cancer and compare their accuracy. Group 1 was Random Forest architecture with a sample size of 10, and Group 2 was a Convolutional Neural Network algorithm with a sample size of 10. They were iterated 20 times to predict the accuracy percentage of identifying melanoma cancer. Compared to Convolutional Neural Network accuracy, the Random Forest method is substantially more accurate (98%) (65%). The random forest technique has a statistical significance of p=0.0018 (p<0.05). The Independent Sample T-test has a high level of importance. In the context of this investigation, the random forest method outperforms the Convolutional Neural Network in melanoma skin cancer detection.