AI Driven Student Information Management: A CNN LSTM Framework for Real Time Attendance Tracking, Grade Prediction, and Record Anomaly Detection

In the modern era of technology, educational institutions are progressively looking for effective ways to handle student information and progress. Using artificial intelligence (AI) and a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture, this study provides a unique Automated Student Records, Grades, and Attendance Management System. By automating grade prediction, attendance tracking, and student data management, the system seeks to reduce administrative workloads. By processing live facial images in an efficient manner, the CNN module improves accuracy and lowers manual errors in real-time attendance marking. Accurate grade projections based on past attendance and performance trends are made possible by the LSTM model's simultaneous analysis of historical academic data. A unified CNN-LSTM architecture also handles student records by flagging them for additional evaluation when it notices anomalies like irregular attendance patterns or grade variations. By continuously learning from incoming data, the AI integration helps the system become more accurate and adaptive over time. In addition to making managing student data easier, the suggested system offers useful information for early performance improvements. By assisting administrators and teachers in making decisions, this multidimensional approach improves the effectiveness of the educational environment. The system is a useful tool for contemporary educational institutions despite difficulties with computational needs and data preparation. It may produce results in real time. The findings of this study highlight the possibility of using artificial intelligence (AI) and cutting-edge machine learning methods to improve overall student record management, which would enhance learning outcomes and student engagement.