Control Ore Processing Quality Based on Xgboost Machine Learning Algorithm

In this paper, we study the problem of quality control of ore processing, using xgboost machine learning algorithm of sklearn module in python, sample interpolation method, 011 minimization loss model and confusion matrix to build xgboost regression prediction model and classification prediction model and error value evaluation model. Firstly, data processing is performed to normalize the data, then xgboost regression prediction is performed for product quality results, and finally confusion matrix is established for model testing, and the parameters are cyclically modified to reach the optimum to obtain various indexes. On this basis, the production and processing data and process data are added, and the data are processed by the spline interpolation method, and then the xgboost machine learning algorithm is used to calculate the prediction results of the pass rate can be obtained from various indicators.