A Recommendation System for Ideation: Enhancing Supermind Ideator

Abstract

Recommendation systems are widely utilized across various domains such as e-commerce, entertainment, and social media to enhance user experience by personalizing content and suggestions. Despite their widespread use, these systems are rarely applied to the ideation process, presenting unique challenges due to the inherently creative and complex nature of generating and developing novel ideas. This thesis details the creation and assessment of a recommendation system for the Supermind Ideator platform, aimed at enhancing the creative ideation processes. The recommendation system leverages machine learning techniques to dynamically adapt to user input statements based on statement "scope", a sub-task that is thoroughly explored and tested in this paper. "Scope" is then integrated into the recommendation system’s static rules-based algorithm to suggest the next best Supermind Design "move". This work not only contributes a practical tool to the field of ideation but also extends the theoretical understanding of recommendation systems in facilitating complex, subjective cognitive tasks.