Living innovation machines: modelling innovation in time and space variable-geometry territorial units using machine learning

ABSTRACT

This paper investigates the innovative intensity (iMID effect) in the local production systems (LPSs) using dynamic territorial units that modifies their geographical boundaries and specialization over time. The paper is based on the idea that the local communities are the real unit of generation of innovation and that they are constantly changing, behaving like a ‘living innovation machine’. To explore this dynamic relationship, the paper applies the Marshallian industrial district (MID) as an approach to industrial change. Then, it focuses on the Marshallian industrial districts (MIDs) as a type of LPS and asks how the innovation effect changes in MIDs and other types of LPSs when dynamic territorial units are used. The differences in innovation intensity between the different types of LPSs are explained for Spain in the period 1991–2014 using new methods of analysis that combine causal analysis, a variable and adaptive geometry of territorial units and industrial specialization, and machine learning methods. The results show that the transformation of an LPS into another type of LPS does not automatically imply a change in innovative capacity, and the type of LPS of origin continues to be relevant in explaining current innovation processes.

KEYWORDS:

• Living innovation machines
• Marshallian industrial districts
• Local production systems
• innovation
• machine learning

Acknowledgements

The authors would like to thank the two anonymous referees for helpful comments made on previous versions of this paper. The usual disclaimers apply.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 Other variables such as serendipity or the extreme effect of some business units would directly affect the innovative intensity without being visibly related to other covariates, which would not affect the causal estimation of the effects of the typology of LPS.

2 The sources of data are SABI and other business directories, Spanish National Institute of Statistics, Ministry of Education and Universities (Boix, Galletto, and Sforzi 2019).

3 For the year 2011, Boix et al. (2018) identification is used, which subdivides very large LLSs when necessary,adding 11 LPS to those identified by Sforzi and Boix (2019).

Additional information

Funding

This work was supported by Ministerio de Ciencia, Innovación y Universidades (Grant Number RTI2018-095739-B-100 and PID2021-128878NB-100).