Construction of quantitative prediction model of metal mineral resources based on big data mining

With the vigorous development of big data technology, the application of data mining program to complete quantitative prediction and evaluation of mineral resources has become a new trend in the development of mineral exploration industry and an important way to promote the digital transformation of traditional prospecting technology. In this regard, this paper will combine geological theory analysis and data mining algorithm to build a quantitative prediction model of metal mineral resources, realize the analysis, processing and visual interpretation of deep geoscience data, and provide necessary data science support for actual mineral exploration. The prediction model takes the machine learning algorithm as the core, and relies on the class libraries such as Numpy, Pandas and Sklearn in Python environment to complete the development and training. Combined with the spatial attribute database in ArcGIS, the prediction elements and importance evaluation indicators are obtained, and the final quantitative prediction results are obtained, and the result evaluation is completed. Practice has proved that the quantitative prediction model of mineral resources based on machine learning algorithm has high prediction accuracy, and the visual results can clearly show the high probability mineral resources areas, which has high practical promotion value.