Student Data Clustering using Machine Learning(Naïve Bayes Classifier & Decision Tree Algorithm)

Student dropout is a significant issue in educational institutions worldwide, posing challenges to both students and educators. Early identification of students at risk of dropping out can enable timely interventions and support, potentially mitigating dropout rates. In this study, we propose a machine learning-based approach for predicting student dropout, leveraging a variety of student-related data. The data include demographic information, academic performance metrics, attendance records, socio-economic factors, and extracurricular activities. We preprocess the data by handling missing values, encoding categorical variables, and scaling numerical features. Feature selection techniques are employed to identify the most relevant predictors of dropout. Various classification algorithms, including logistic regression, decision trees, random forests, support vector machines, and neural networks, are evaluated for their predictive performance. The models are trained on historical data, split into training and testing sets, and evaluated using metrics such as accuracy, precision, recall, F1-score, and area under the ROC curve (AUC-ROC). Hyperparameter tuning is performed to optimize the models' performance further. The results demonstrate the effectiveness of the proposed approach in accurately predicting student dropout. Additionally, we provide insights into the factors contributing most significantly to dropout risk, facilitating targeted interventions by educational institutions. This study contributes to the field of educational data mining by offering a practical framework for dropout prediction, thereby empowering educators to proactively address the issue of student attrition. Future research directions include the integration of additional data sources and the development of personalized intervention strategies based on predictive analytics.