End-user devices, such as mobile phones and tablets, have become essential tools for accessing smart homes. Consequently, user authentication, one of the most important security factors, needs to be considered to prevent unauthorized access to home devices. Although mobile phones are equipped with different means of authentication such as fingerprint readers, these methods are only employed at the time of access; hence, countermeasures should be developed to overcome potential threats. This paper presents a continuous user authentication model based on apps access usage on mobile devices. To validate the presented model, two public real-world datasets collected from real users over a long period, are used. The model is evaluated for its ability to differentiate between users utilizing shared apps at the same daily intervals. Moreover, various classification approaches regarding legitimate user classification in compliance with the history of apps usage are evaluated. The results demonstrate the capacity of the presented method to authenticate users with high true positive and true negative rates.