Data-driven prospectivity modeling based on deep learning, particularly supervised learning, has demonstrated outstanding performance for mineral exploration targeting in the past years, thanks to its powerful feature learning ability. However, this approach necessitates a substantial amount of large, high-quality labeled training data, and the scarcity of known mineral deposits poses significant challenges in constructing a high-performance mineral prospectivity prediction model. Self-supervised contrastive learning can alleviate this problem by exploiting large amounts of readily available unlabeled data. In this study, we utilized geochemical element data from the Malanyu district to train a self-supervised contrastive learning model. This model was then employed to predict gold mineral prospectivity, and its accuracy was compared with supervised learning method. The results show that the self-supervised contrastive learning model has higher performance in prospectivity prediction than the supervised learning model and its recognition accuracy reaches 100.00%, which is 7.41% higher than that of the supervised learning model ResNet50 and 14.81% higher than that of the supervised learning model MobileNetV2. At the same time, the prediction results of gold prospecting have a strong consistency with the known gold deposits in this district. This study demonstrates the feasibility of applying the self-supervised comparative learning model to the prediction of gold prospects, and it is of great significance to realize intelligent prediction of mineral resources.