Identifying Emerging Technologies and Leading Companies using Network Dynamics of Patent Clusters: a Cybersecurity Case Study

TL;DR

This paper presents a rapid, scalable network science-based system that analyzes patent data to identify emerging technologies and influential companies, demonstrated through a cybersecurity case study.

Contribution

It introduces a generalizable, computationally efficient method combining patent valuation and network analysis to forecast industry leaders and innovations.

Findings

Emerging technologies show increasing patent value and cluster size.

Key influential companies are identified through network centrality.

Startups with few impactful patents are highlighted as attractive investments.

Abstract

Strategic decisions rely heavily on non-scientific instrumentation to forecast emerging technologies and leading companies. Instead, we build a fast quantitative system with a small computational footprint to discover the most important technologies and companies in a given field, using generalisable methods applicable to any industry. With the help of patent data from the US Patent and Trademark Office, we first assign a value to each patent thanks to automated machine learning tools. We then apply network science to track the interaction and evolution of companies and clusters of patents (i.e. technologies) to create rankings for both sets that highlight important or emerging network nodes thanks to five network centrality indices. Finally, we illustrate our system with a case study based on the cybersecurity industry. Our results produce useful insights, for instance by highlighting (i) emerging technologies with a growing mean patent value and cluster size, (ii) the most influential companies in the field and (iii) attractive startups with few but impactful patents. Complementary analysis also provides evidence of decreasing marginal returns of research and development in larger companies in the cybersecurity industry.