Web engine for investigating consumer consideration

Abstract

Today consumers are presented with a plethora of products each time they want to make a purchase. Sometimes they have up to thousands of options and configurations to pick from and yet many consumers are shown to initially screen this size to create a more manageable set to truly consider in an in-depth way. Companies today are looking for ways to ensure that their products make it into the smaller consideration sets of consumers in order to increase the probability of sales. This thesis documents the design of a web engine that provides a survey framework for investigating algorithms that aim to predict which products a user will place in their consideration set as well as to aid in investigating the factors that can lead to the modification of rules that govern a consumer's consideration set. Firstly I evaluated and documented the improvements required from older systems created by the research group. Then over the course of two studies I designed a highly modular system that is a new iteration of the older versions. Finally, more than 3500 participants used the system during field tests and the system was successful in mitigating the previous issues and delivering a better user experience as well as collecting the necessary data. This project lays the groundwork for a platform that can be used for generally investigation and testing consideration predictive algorithms in various retail spaces.