The most common and possibly lethal type of cancer, skin cancer, will be most people’s first encounter with it. Information technology must also be used to make a skin cancer diagnosis. This emphasizes how important it is to create and use extremely efficient deeplearning techniques for quick and accurate identification and prevention of skin cancer. In this paper, the Deep Convolution Neural Network (DCNN) is recommended for automated skin cancer diagnosis. The original contribution of this study is the application of a deep convolution neural network with 12 stacked processing layers to increase the precision of skin cancer detection and diagnosis. The results of this study have led researchers to the conclusion that deep learning methods are more effective than machine learning for detecting skin cancer. As a result, automated evidence-based skin cancer identification may increase the accuracy and proficiency of pathologists. In this study, we introduce a deep convolution neural network (DCNN) network that uses deep learning to successfully identify between malignant and benign skin lesions. The results of this study have led researchers to the conclusion that deep learning methods are more effective than machine learning for detecting skin cancer. As a result, automated evidence-based skin cancer identification may increase the accuracy and proficiency of pathologists. In this study, we introduce a deep convolution neural network (DCNN) network that uses deep learning to successfully identify between malignant and benign skin lesions.