<![CDATA[There are still significant drawbacks to traditional attendance techniques, like those employed at PT Cloud Hosting Indonesia, including the possibility of fraud, imprecise data capture, and reliance on manual input. The goal of this project is to use Convolutional Neural Network (CNN)-based facial recognition technology, which is implemented using the Face-API.js package, to design and construct an online employee attendance system. To guarantee that attendance can only be completed within a specified office radius, the system is outfitted with geolocation validation. This system's practical advantages include lowering the workload of human resources personnel, increasing the precision of attendance records, and stopping the practice of entrusted attendance. In order to protect user privacy and minimize server load, the facial recognition procedure is carried out directly on the client side (browser). The Agile Scrum system development methodology, which is used iteratively to adapt to user needs, is combined with a quantitative approach in this study. The black-box method is used for testing, and a confusion matrix is used to evaluate performance. According to the test findings, all characteristics function as intended, and the system can identify user faces from 15 registered face samples with an accuracy rate of 86.67%. The efficiency, transparency, and security of this system are better than those of traditional attendance techniques and GPS-based biometrics alone. Face recognition technology and location validation combine to create a digital solution that is suitable, secure, and suitable for use in organizations with flexible or shift-based work schedules.]]>
