Abstract: The stability control of surrounding rock in coal roadway is the key to ensure the safe and efficient mining of coal mine. In this paper, machine learning method is introduced to predict the roof displacement of coal roadway in advance. Firstly, eight important influence indexes of roof displacement of coal roadway are se-lected, and the prediction database of roof displacement of coal roadway is established, and the correlation and importance of the data are analyzed. Then, based on RF, GA-SVM and GA-ANN, three kinds of coal roadway roof displacement prediction models were established respectively, and RMSE, MAE and R2 were selected to evaluate the performance of the models. The results show that the RF model has the best test performance, R2 = 0.909, RMSE = 20.475, MAE = 16.790, while the GA-ANN model has the worst performance. The ten-fold cross-validation method was used to verify the reliability of the RF model and the GA-ANN model, and it is found that the stability of RF model is higher, with an average R2 of 0.891. Finally, the RF model is applied to the 2-1121 roadway of Ganhe Coal Mine. The absolute error between the predicted value and the actual value is 19 mm, and the relative error is 11.18 %. The RF model makes a relatively accurate prediction of the roof displacement of the coal roadway.