Multi-View Representation Learning for Regional Opportunity Spaces and Industrial Path Development

Philipp Stark (), Alexandros Sopasakis (), Ola Hall () and Markus Grillitsch ()
Additional contact information
Philipp Stark: Department of Human Geography, Lund University, Postal: Sölvegatan 10, 223 62 Lund, Sweden
Alexandros Sopasakis: Centre for Mathematical Sciences, Lund University, Postal: Sölvegatan 18, 223 62 Lund, Sweden
Ola Hall: Department of Human Geography, Lund University, Postal: Sölvegatan 10, 223 62 Lund, Sweden
Markus Grillitsch: Department of Human Geography, Lund University, Postal: Sölvegatan 16, 223 62 Lund, Sweden

No 2026/12, Papers in Innovation Studies from Lund University, CIRCLE - Centre for Innovation Research

Abstract: Regional opportunities for industrial development arise when local conditions favor particular economic activities. These conditions depend in part on a region’s existing industry profile and on the economic relationships among its activities. Heterogeneous data sources on mobility, production, and firm ownership provide complementary evidence about this underlying industrial structure. We therefore develop a multi-view representation-learning framework for industries that integrates these different sources into a shared latent representation. By using graph diffusion, the framework captures both direct and indirect connections between industries. Applied to Swedish industries over three decades and three classification versions, the learned representation places industries from different classification periods within a common latent space. To evaluate this operationalization of opportunity, we construct an opportunity-density measure by combining latent similarity with local industry size. Higher opportunity density is consistently associated with industry entry and startup formation and with lower industry exit. Across classification periods, a one-standard-deviation increase in opportunity density is associated with 5.3–6.2 percentage-point higher industry-entry probabilities (118–136% of baseline rates), 8.9–13.8 percentage-point lower industry-exit probabilities (147–209%), and 1.1–1.7 percentage-point higher startup-formation probabilities (131–187%). Opportunity density remains associated with these outcomes in 41 of 42 models after accounting for information contained in the individual data sources. Our machine-learning framework shows how heterogeneous data can be integrated into a common latent structure and used to operationalize regional opportunity spaces, providing a new approach to studying industrial path development.

Keywords: Regional opportunity spaces; Industrial path development; Industry relatedness; Multi-view representation learning; Regional diversification (search for similar items in EconPapers)
JEL-codes: C45 L16 R11 (search for similar items in EconPapers)
Pages: 46 pages
Date: 2026-10-13
Note: This work was supported by FORMAS (grant no. 2022-153657) and seed funding from the AI Lund Initiative at Lund University through the project “Temporal Harmonization of Industry Classifications with Swedish Register Data.” The work of A.S. was partially supported by eSSENCE (grant no. 156938) and the Swedish National Space Agency (grant no. 2025-00016). The computations were enabled by resources provided by the National Academic Infrastructure for Supercomputing in Sweden (NAISS), partially funded by the Swedish Research Council through grant agreement no. 2022-06725.
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.lub.lu.se/piis/article/view/30120/25887 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hhs:lucirc:2026_012

Access Statistics for this paper

More papers in Papers in Innovation Studies from Lund University, CIRCLE - Centre for Innovation Research CIRCLE - Centre for Innovation Research, Lund University, PO Box 117, SE-22100 Lund, Sweden. Contact information at EDIRC.
Bibliographic data for series maintained by Torben Schubert ().