The yin yang of AI: Exploring how commercial and non-commercial orientations shape machine learning innovation

Abstract

The scale of the potential implications of machine learning (ML) has prompted discussions on the issues of corporate control and technological openness. However, how commercial and non-commercially oriented organisations each contribute to ML progress remains an open question. This study uses the recombinant innovation perspective as a lens to explore recombinant patterns across projects in an open source software (OSS) environment – where a great deal of ML innovation occurs – and assess how commercial orientation influences such patterns. It builds on a unique dataset containing data on 28,443 OSS projects, their code dependencies and the organisations owning them. Exploratory analyses reveal that ML projects combine larger and more diverse components, and produce more atypical combinations in shorter timeframes than other OSS projects, and that both company and non-company owned ML projects contribute to such recombinant atypicality. Regression analyses indicate that company owned ML projects tend to rely more on distant combinations of technical knowledge, whereas non-company owned ML projects tend to produce more novel combinations of application ideas. By extending the theories of recombinant innovation and motivation in OS innovation into a new setting – ML technology, this study contributes to both literatures by confirming that the link between distant recombination and innovation still holds in contexts characterised by complex search spaces, and by suggesting complementarities between commercial and non-commercial orientations in OSS environments rich in knowledge diversity and recombinant activity.