Providing a Better User - Interface to Explore Large Product

Purchasing a product on the Web is difficult as the product space is gigantic, users often have difficulty specifying what they want, and current systems do not help users leam as they explore the space. The idea in this thesis is to utilize a genetic algorithm to efficiently navigate this hyperspace. From examples, product specifications can be inferred and used to explain the functioning of the genetic algorithm. To test these ideas, we built the Auto-ficial Life system, a generic UI akin to Karl Sims' Genetic Images or Richard Dawkins Blind Watchmaker[23][10]. Explanation and control features augment the system's operation. As a result, users efficiently traverse the hyperspace because of the ease in expressing imprecise preferences. This system was implemented in two product domains, that of cars and men's shoes, and provided efficient navigation in both domains. Thesis Supervisor: Henry Lieberman Title: Research Scientist, MIT Media Lab