Traditional method for evaluating student performance primarily rely on academic scores or grades alone, which often fail to capture the diverse patterns of student engagement and learning behavior. This research aims to analyze and classify female students based on their academic and engagement attributes using clustering techniques. By applying unsupervised machine learning methods such as K-Means, Hierarchical Clustering, and Gaussian Mixture Models (GMM) and SAW method, the study segments students into meaningful groups reflecting varying learning patterns. The integration of academic and behavioral data for student performance prediction has gained prominence in educational data mining, particularly in the context of blended learning environments. The educational dataset often show distinct engagement and participation patterns that are not always reflected in grades alone. By combining clustering techniques with a composite Performance Quotient (PQ), calculated through the Simple Additive Weighting (SAW) method, this study aims to fill that gap. The dataset comprises multiple academic and engagement attributes, including quiz averages, previous grades, attendance, online activities, and prior knowledge. A Performance Quotient (PQ) was calculated using a customized SAW formula that assigns weighted importance to these variables, providing a comprehensive measure of student performance. The study gives comparative analysis of these clustering algorithms with specific number of clusters through cluster evaluation metrics like Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Score. The proposed approach offers valuable insights for educational institutions to implement data-driven interventions and personalized learning strategies, particularly learning pattern of female students in blended learning contexts. The motivation is to provide educators with actionable insights to segment students into meaningful groups (e.g., high-performing, disengaged, at-risk), so they can deliver targeted support, enhance learning outcomes, and promote inclusive, gender-responsive academic strategies.