Educational institutions generate large volumes of student data through academic records, attendance, assessments, skill development activities and placement processes. However, effective utilization of these data for academic and placement decision making remains challenging. This paper presents a Student Performance Analytics and Placement Prediction Framework integrating data analytics, machine learning, clustering and business intelligence visualization. The framework uses an initial dataset of 75 student records and 22 attributes containing academic, extracurricular behavioral, and employability, student-risk related information. A Placement variable is subsequently derived using predefined Previous CGPA, Aptitude Score and Coding Score criteria for the placement classification experiment. Linear Regression is applied for academic performance prediction, Logistic Regression for placement classification, Decision Tree for performance classification, and K Means for student segmentation. A Power BI dashboard is developed to visualize placement outcomes, academic performance, attendance, employability skills, performance categories and dropout risk. Logistic Regression achieved an accuracy of 93.33 percent with a weighted F1 score of 0.93 on the evaluated test set, while Linear Regression obtained an MSE of 1.5467 and an Rē score of -0.4373. Decision Tree classification achieved an accuracy of 40.00 percent. Since the placement labels were derived using predefined academic and technical criteria, the placement classification result should be interpreted as an evaluation of the defined rule-based labeling scheme rather than as evidence of generalized real-world placement prediction.The results indicate the potential of the proposed framework for student segmentation, placement analysis and data driven academic decision support, while the limited dataset size restricts generalizability.
Student performance analytics; placement classification; machine learning; educational data analytics; Power BI; student segmentation; academic performance