Towards Understanding the Effects of Practice on Behavioural Biometric Recognition Performance

Behavioural biometrics looks at discriminative features of a person's measurable behaviour, which is known to show high variance over long stretches of time. In psychology, a significant portion of this behavioural variance is explained by an individual improving their skill at performing behaviours, mostly through practice. Understanding what the effects of practice are on biometric recognition performance should allow us to account for much of this variance, as well as make individual behavioural biometric studies easier to compare [15]. We hypothesize that more accumulated practice will lead to both more stable and increased recognition performance. We argue that these are significant effects and show that practice in general is under-investigated. We introduce a novel method of analysis, the Start-to-Train Interval (STI)/Train-to-Test Interval (TTI) contour plot, which allows for systematic investigation of how recognition performance develops under increased practice. We applied this method to three data sets of a Discrete Sequence Production (DSP) task, a task that consists of repeatedly (500+ times) typing in a simple password, and found that more practice both significantly increases recognition performance and makes it more stable. These findings call for further investigation into the effects of practice on recognition performance for more standard behavioural biometric paradigms.