Measuring the Direction of Innovation: Frontier Tools in Unassisted Machine Learning
44 Pages Posted: 4 Jun 2020 Last revised: 2 Aug 2021
Date Written: August 1, 2021
As strategy research has increasingly recognized the roles of innovation and knowledge as drivers of firm- and industry-level outcomes, greater attention has been given to the effort to identify relationships among ideas and the distances between knowledge bases. In this paper, we develop a methodology that infers the mapping of the knowledge landscape based on researchers’ text documents. The approach is based on an unassisted machine learning technique, Hierarchical Dirichlet Process (HDP), which flexibly identifies patterns in text corpora. The resulting mapping of the knowledge landscape enables calculations of distance and movement, measures that are valuable in several contexts for research in strategy and innovation. We benchmark demonstrate the benefits of our approach in the context of 44 years of USPTO data.
Keywords: Innovation, topic modeling, machine learning, knowledge landscape, distance in knowledge space, movement in knowledge space, diversity, knowledge trajectories, rate and direction of innovation
JEL Classification: O30, O31, O33, O39
Suggested Citation: Suggested Citation