A method (300) for identifying a characteristic of a user of a personal care device (10) comprising a sensor (28), a controller (30), and a database (34), comprising the steps of: training (320) the device with training data, comprising the steps of: (i) obtaining (322) sensor data for at least one personal care session for each of at least two different users； (ii) extracting (324), via an extraction module, a plurality of features from each of the personal care sessions； and (iii) training (328), using the extracted features, a classifier to identify a characteristic of each of the at least two different users of the device； obtaining (330) sensor data for at least part of a new personal care session； extracting (340) a plurality of features from the sensor data for the new personal care session； and identifying (360), using the trained classifier, a characteristic of the user of the device.
