Data-intensive evaluation of design creativity using novelty, value, and surprise

The increasing availability of large quantities of product-related data provides an opportunity to augment human designers with analytical models for evaluating the creativity of a new design. In this paper we describe three characteristics of a creative design: novelty, value, and surprise. We present an analytical framework for computationally evaluating the creativity of a new design. Building on our previous work, we associate each characteristic with a computational process, and develop a new model for evaluating surprise using predictive analytics. We describe an implementation of our analytical models as applied to a data-set of mobile devices. We report on the most surprising devices identified by our models and their corresponding novelty and value scores, and conclude by discussing the broader applications and implications of an analytical approach to evaluating creative designs.