Measuring Transaction Costs in Public Sector Contracting Through Machine Learning and Contract Text - Research Article

Aug 5, 2026

Upload by Rowan

Transaction cost (TC) theory is widely used in the social sciences, but core constructs such as measurability and asset specificity are difficult to measure systematically in empirical work. Existing government contracting research relies heavily on limited survey-based approaches from US municipal and county studies. This study introduces a preregistered method that uses machine learning on contract text, validated with out-of-sample performance and supported by a manager survey. The approach yields new product-level TC measures for 176 products across EU procurement directives, enabling broader TC applications in public management research.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Transaction cost theory and measurement challenges

Preregistered machine learning method

Validation and out-of-sample performance

Generated TC database and research implications

Roskilde University Measuring Transaction Costs in Public Sector Contracting through Machine Learning and Contract Text Potoski, Matthew; Lund-Sørensen, Bjarke; Petersen, Ole Helby Published in: Public Administration Review DOI: 10.1111/puar.13947 Publication date: 2025 Document Version Publisher's PDF, also known as Version of record Citation for published version (APA): Potoski, M. , Lund-Sørensen, B. , & Petersen, O. H. (2025) . Measuring Transaction Costs in Public Sector Contracting through Machine Learning and Contract Text. Public Administration Review, Early view. [https://doi.org/10.1111/puar.13947](https://doi.org/10.1111/puar.13947) General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain. • You may freely distribute the URL identifying the publication in the public portal. Take down policy If you believe that this document breaches copyright please contact [rucforsk@kb.dk](rucforsk@kb.dk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 14. May. 2025 Public Administration Review RESEARCH ARTICLE OPEN ACCESS Measuring Transaction Costs in Public Sector Contracting Through Machine Learning and Contract Text Matthew Potoski1 | Bjarke Lund-Sørensen2 | Ole Helby Petersen2 1Bren School of Environmental Science and Management, University of California, Santa Barbara, California, USA | 2Department of Social Sciences and Business, Roskilde University, Roskilde, Denmark Correspondence: Ole Helby Petersen ([olehp@ruc.dk](olehp@ruc.dk)) Received: 11 April 2024 | Revised: 12 February 2025 | Accepted: 17 February 2025 Funding: This research was supported by the Independent Research Fund Denmark (Grant no. 9061-00020B) . Keywords: contract management | machine learning | transaction costs ABSTRACT Transaction cost (TC) theoretical constructs are central to research throughout the social sciences, yet key concepts, such as measurability and asset specificity, often defy systematic empirical measurement. In government contracting research, empirical measurements of key TC theoretical constructs are limited to the International City/County Management Association's surveys of US municipal and county governments. We present a preregistered method using machine learning algorithms to generate product-level TC measures from contract text data and a government contract manager survey. We verify the algorithms' out-ofsample performance and use them to generate TC measures for additional products from corresponding contract text data. The result is a publicly available database of new TC measures for 176 diverse products and services covered in the European Union's Common Procurement Directives. These new measures facilitate the application of the TC framework across public management, including research on government contracting, collaboration, networks, and governance. The transaction cost (TC) theoretical framework (Coase 1988; Williamson 1979, 1985) identifies factors that influence the costs, benefits, and risks inherent in social interactions. Unsurprisingly, the framework has a robust presence throughout the social sciences, with applications in areas such as organizations (Scott 1987, 2004), financial markets (Hasbrouck 1993), governments (North 1990, 1991), business management (Geyskens et al. 2006), and self-governance (Ostrom 1990) .1 In public administration research, the TC framework has guideda generation of scholarship by identifying con

FAQs

What problem does the article address in measuring transaction costs?

Key TC constructs in theory, such as measurability and asset specificity, often resist systematic empirical measurement. The paper highlights limited existing measures in government contracting research.

How does the study generate transaction cost measures?

It uses machine learning algorithms to derive product-level TC measures from contract text data. The method is preregistered and also incorporates a government contract manager survey.

What is the scope and impact of the resulting dataset?

The method produces new TC measures for 176 diverse products and services covered under EU Common Procurement Directives. These measures support applying the TC framework across research on public contracting, collaboration, networks, and governance.

Aug 5, 2026

Upload by Rowan