DATA-DRIVEN APPROACHES TO EDUCATIONAL EQUITY: PREDICTING AND RESOLVING GENDER-BASED ACADEMIC DISPARITIES

Subject Area: ARTIFICIAL INTELLIGENCE: MACHINE LEARNING FOR GENDER DISPARITY RESOLUTION

This research addresses gender disparity in academic achievement through an innovative approach, integrating predictive analytics and strategic mitigation strategies. Employing Python and Spyder as the primary programming tools, the study utilizes the Structured Systems Analysis and Design Method (SSADM) to systematically explore the academic landscape. At its core, the research implements a Stack Ensembled Data Analytics technique, combining five models—K-Nearest Neighbors (KNN), Logistic Regression, Decision Tree, Support Vector Machine, and Random Forest. This ensemble approach enhances predictive accuracy and robustness, offering a nuanced understanding of factors contributing to gender-based academic disparities. Machine learning libraries, including Pandas, NumPy, StandardScaler, and LabelEncoder, along with evaluation metrics such as Accuracy Score and Confusion Matrix, contribute to a comprehensive analysis. The models exhibit commendable performance during the evaluation phase, demonstrating the strength of the chosen approach. SSADM ensures a structured process from data collection to model implementation and evaluation. The significance of the research lies in its ability to predict gender-based academic disparities and propose effective mitigation strategies accurately. Leveraging ensemble models unravels intricacies contributing to performance variations, empowering educational institutions with actionable insights for targeted interventions. This project significantly contributes to the discourse on educational equity by introducing a data-driven framework that predicts disparities and facilitates strategic interventions. The successful integration of Python, SSADM, and stack-ensemble models underscores the versatility of the approach, positioning it as a valuable tool for researchers, educators, and policymakers. In the evolving academic landscape, this research offers a timely contribution to global efforts for a more equitable and inclusive educational system.