This research paper introduces an innovative automated student attendance system that leverages facial recognition technology to improve the accuracy and efficiency of attendance tracking in educational institutions. Central to the system’s functionality are advanced components such as convolutional neural networks and the InsightFace framework, which enable real-time facial analysis. In addition, Redis is employed for robust database management, ensuring smooth data retrieval and storage. The system effectively tackles critical issues like inaccuracies in attendance records and the rise of proxy attendance, challenges that have become more pronounced in the wake of the COVID-19 pandemic. Its meticulously designed workflow encompasses data collection, feature extraction, database integration, and real-time predictions, utilizing cosine similarity metrics for identity verification. With a commendable accuracy rate of 91 percent, the system showcases its reliability, though it still encounters challenges related to facial occlusions and variable lighting conditions that can obstruct recognition. Future research will expand the dataset to include a wider range of demographic profiles, enhance recognition capabilities in adverse conditions, and integrate additional features such as behavior recognition. This comprehensive approach aims to create a more inclusive and efficient attendance-tracking solution, addressing the evolving needs of modern educational environments.