Enhancing Student Performance Prediction Using Greylag Goose Optimization

Led a team to implement the Greylag Goose Optimization (GGO) algorithm for enhancing a Multilayer Perceptron (MLP) Regressor, reducing Mean Squared Error (MSE) significantly.

The project focused on hyperparameter tuning and comparative analysis with other metaheuristic algorithms, improving predictive accuracy and enabling targeted interventions for at-risk students.