The use of inertial sensors such as accelerometers and gyroscopes, which are now often embedded in many wearable devices, has gained attention for their applicability in user authentication applications as an alternative to PINs, passwords, biometric signatures, etc. Previous works have shown that it is possible to authenticate users based on fine-grained kinematic behavior profiles like gait, hand gestures and physical activities. In this work we explore the use of actigraphy data for user recognition based on daily patterns as opposed to fine-grained motion. One of the advantages of the former, is that it does not require to perform specific movements, thus, easing the training and calibration stages. In this work we extracted daily patterns from an actigraphy device and used a random forest classifier and a majority voting approach to perform the user classification. We used a public available dataset collected by 55 participants and we achived a true positive rate of 0.64, a true negative rate of 0.99 and a balanced accuracy of 0.81.