Paper accepted in the 15th International Conference on Knowledge Management and Information Systems, KMIS 2023

A paper is accepted in the 15th International Conference on Knowledge Management and Information Systems

  • Title: Discovering Potential Founders based on Academic Background
  • Authors: Arman Arzani, Marcus Handte, Matteo Zella, Pedro José Marrón
  • Abstract: Technology transfer is central to the development of an iconic entrepreneurial university. Academic science has become increasingly entrepreneurial, not only through industry connections for research support or transfer of technology but also in its inner dynamic. To foster knowledge transfer, many universities undergo a scouting process by their innovation coaches. The goal is to find staff members and students, who have the knowledge, expertise, and the potential to found startups by transforming their research results into a product. Since there is no systematic approach to measure the innovation potential of university members based on their academic activities, the scouting process is typically subjective and relies heavily on the experience of the innovation coaches. In this paper, we study the discovery of potential founders to support the scouting process using a data-driven approach. We create a novel data set by integrating the founder profiles with the academic activities from 8 universities across 5 countries. By applying machine learning methods, we try to answer three questions. First, is it possible to accurately classify founders and non-founders by extracting features from their academic activities? Second, what are the main features that identify founders? Third, is it possible to predict the future founding probability of university members to objectify the scouting process? Our analysis shows that using a Random Forest (RF), it is possible to differentiate founders and non-founders with an average accuracy of 79%. This accuracy remains mostly stable when applying an RF trained on one university to another, suggesting the existence of a generic founder profile. The detailed analysis indicates a high significance of the career path as well as patent- and grant-related features amongst others. Finally, we show that using an RF, it is possible to exploit these features to predict the future founding probability up to 3 years in advance with an accuracy of 80%.