This study uses the random forest algorithm to estimate the performance of high-performance concrete made of fiber glass. After conducting in-depth research on massive experimental data, we decided to use the random forest method and verified its effectiveness. The paper focuses on the compressive performance of cement based on random forest. Research has found that the mean squared error (MSE) of the random forest model is 0.9823, the decision coefficient is 0.9567, the root-mean-squared error (RMSE) is 0.2054, and the mean absolute error (MAE) shows high accuracy and reliability, indicating that the random forest model has high accuracy and reliability in predicting the performance of glass fiber high-performance concrete.