Hou, W and Ran, W (2025) Unveiling the effects of influencing factors on PPP project capital structure in China using machine learning. Engineering, Construction and Architectural Management, 32(12), pp. 8621-8641. ISSN 0969-9988
Abstract
Purpose – This study aims to investigate the determinants of the capital structure of public–private partnership (PPP) projects in China and the nonlinear relationship between them. Design/methodology/approach – First, this study identifies potential factors that can influence the capital structure of PPP projects based on literature and theoretical analysis. Second, this paper collects data from PPP projects in China and empirically investigates them using multiple linear regression and machine learning methods. Finally, for machine learning model results, this paper adopts the Shapley additive explanations to interpret them. Findings – The results show that project size, contract duration, number of sponsors, urbanization level and regional openness are key factors influencing project capital structure, and there is a nonlinear relationship between all these factors and capital structure. Research limitations/implications – Theoretically, this study complements the influencing factors of PPP project capital structure and reveals their nonlinear relationship. Practically, the findings of this study can help PPP project participants formulate project capital structure more scientifically. Practical implications – Practically, the findings of this study can help project managers to recognize the important factors affecting the capital structure of PPP projects and formulate capital structure more scientifically. Moreover the results are conducive to policymakers to predict a reasonable capital structure for PPP projects and better control project risks. These research findings can also help creditors make more accurate loan decisions and promote project success to meet the needs of the general public. Originality/value – Most existing literature has studied the linear relationship between influencing factors and the capital structure of PPP projects. This study uses machine learning models to explore the nonlinear relationship between influencing factors and the capital structure of PPP projects and explains the working principles.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | capital structure; influencing factor; machine learning; PPP; shap |
| Index terms: | influencing factor, urbanization, project success, project manager, partnership, determinant, duration, capital structure, methodology, machine learning, China |
| Subjects: | artificial intelligence, profession, risk assessment, project controls, partnership management, project management theory and practice, urban planning, economic analysis, research methods, Geography |
| Topics: | Digital Applications, Time Control, Business Strategy, Research Practice, Stakeholder Management, Roles and Professions, Governance, Project Management, Geographical Context, Risk Management |
| Descriptive scope: | 3 PCT |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here