Optimizing Student Performance with GridSearchCV Using Random Forest Classifier Method to Enhance Learning Outcome Prediction

Predicting student performance is becoming increasingly important because it plays a major role in the sustainable development of countries, which depend on effective education systems to produce a generation of leaders in various aspects of life, including science, economy, social, and military. Advances in educational technology have changed academic performance analysis, allowing for more accurate and databased predictions of student performance This research aims to optimize the performance of student learning outcome prediction by using the Random Forest Classifier method which is improved through the GridSearchCV technique. This research focuses on improving accuracy and efficiency in predicting student learning outcomes based on historical data and variables used. The data used in this study were collected from various educational sources that included student academic achievement records, demographic data, and other related variables. The Random Forest Classifier method is applied as the main prediction model. The GridSearchCV technique is used to find optimal combinations of parameters that improve the model’s performance. Model evaluation is carried out using accuracy, precision, recall, and F1-score metrics to ensure the reliability of predictions. The results show that the use of GridSearchCV significantly improves the performance of the Random Forest Classifier model. The optimized model is able to achieve a higher prediction accuracy of 0.89. This improvement was also seen in other evaluation metrics, which showed an overall improvement in the model’s predictive ability to student learning outcomes.