Examined actual educational data from Kaggle
used and contrasted a number of machine learning algorithms, including SVM, Random Forest, XGBoost, Neural Networks, and Decision Trees.
interpreted model behavior and produced useful educational insights using Explainable AI (XAI) techniques such as SHAP values.
ANN (MLP) and XGBoost models were used to achieve up to 95% accuracy.
In addition to my expertise in data preprocessing, model evaluation, feature engineering, and result visualization, I possess strong technical skills in Python (Pandas, Scikit-learn, XGBoost, Matplotlib, and Seaborn).
