Automatic interface optimization through random exploration of available elements

Leonardo Anjoletto Ferreira, Andrey Araujo Masiero, Plinio Thomaz Aquino Jr., Reinaldo Augusto da Costa Bianchi

Abstract: The Keystroke-Level Model (KLM) is an interface evaluation method that use as metric the time needed to perform an executed action to complete a given task. The description used in KLM is very similar to the formalism that Markov Decision Process (MDP) uses to describe a domain, in which an artificial agent must perform a sequence of actions in order to solve a problem. This work presents a way to model a user's interaction with an interface using MDP combined with KLM in order to optimize a set of parameters and find the best set of interface components for a user. Results show that by changing the metrics of the KLM, the MDP finds different solutions that may be combined to generate an interface tailored for a given user.