A significant amount of gold is produced in Jiaodong Peninsula, North China. The Jiaojia-type (fracture-disseminated rock type) and Linglong-type (sulfide-bearing quartz vein type) are the most two important types of gold deposits related to hydrothermal fluids in this region. Therefore, understanding the differences in ore-forming fluids between these two types of gold deposits is crucial for genesis and exploration, yet there is a lack of comprehensive documentation on this subject. As an important gold-bearing mineral, pyrite plays a significant role in revealing the characteristics of ore-forming fluids. In this paper, the big data analysis and machine learning methods are applied to discriminate the types of the gold deposits. The factor analysis (FA) and the random forest (RF) algorithm to examine the presence of trace elements of pyrite in Jiaojia- and Linglong-type gold deposits. The FA analysis reveals that the elements in pyrite can be grouped into four factors: F1 (Ag-Pb-Bi), F2 (Cu-Zn), F3 (Co-Ni), and F4 (Au-As). This classification is likely influenced by the distribution of trace elements within pyrite. The interconnectedness among the F1-F2-F3-F4 components implies a common source of ore-forming fluids between these two gold deposit types. At the same time, the random forest model highlights Bi, Zn, and As as the most distinguishing elements in pyrite between the two deposit types. These findings suggest that Jiaojia- and Linglong-type gold deposits have distinct temperatures of the ore-forming fluids and at the extension of the ore-controlling structure of Jiaojia-type ore body may exist the Linglong-type ore body. Accordingly, a machine learning model was developed for detecting the two types of gold deposits. This pioneering research blends big data analytics and artificial intelligence to enhance the classification of mineral deposits, offering a novel approach to mineral exploration in the Jiaodong region.