Students’ performance in higher education reflects their overall quality in higher education. By predicting the performance, students with greater learning problems can be screened out early and given appropriate guidance. To predict students’ performance in English, the knowledge information of courses, examination papers, and historical examination records are used to build a feature project of students’ examinations. Meanwhile, the features strongly correlated with their performance are filtered out. Then the next step of performance prediction is carried out. The results showed that a neural network long and short-term memory performance prediction model incorporating an attention mechanism was more effective than other models in predicting English performance in higher education. Further experiments found that the model reduced the error by 1.04% on the MAE metric, 0.53% on the RMSE metric, and increased its value by 4.12% on the R2 metric. Adding the new feature dataset led to better forecasting by the Att-LSTM model in all metrics. This indicated that the enhanced dataset temporality could improve the effectiveness of the Att-LSTM model in predicting English grades in higher education. The stacked integrated prediction model, by integrating multiple strong regressors, can avoid poor prediction and excessive overall bias due to one regressor and increase the soundness and prediction precision of the mode.