Analyzing the Differential Impact of Variables on the Success of Solicited and Unsolicited Private Participation in Infrastructure Projects Using Machine Learning Techniques

Aug 6, 2026

The study examines how key variables influence the success of solicited and unsolicited private participation in infrastructure (PPI) projects. Data covering 8,674 PPI projects, mainly from the World Bank database, is analyzed using a machine learning framework. The workflow tackles data challenges through imputation, oversampling, and standardization, then applies Random Forest, Artificial Neural Networks, and logistic regression for classification. Performance is evaluated with diverse metrics, showing that roughly half of the variables affect both project types similarly, while institutional factors vary in impact—helping explain higher failure rates of unsolicited projects and guiding investors, policymakers, and practitioners.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages46

Reading Time1 h 56 min

AccessFree to download

Abstract

Introduction

Public-private partnership structure of PPI projects

Motivation: investment trends and failure challenges

Solicited vs. unsolicited PPI project initiation

Ayat, M Ullah, M Pervez, Z Lawrence, J Kang, C.W and Ullah, A (2024), "Analyzing the differential impact of variables on the success of solicited and unsolicited private participation in infrastructure projects using machine learning techniques", Engineering, Construction and Architectural Management, Vol. ahead-of-print No. ahead-of-print. [https://doi.org/10.1108/ECAM-01-2024-0134](https://doi.org/10.1108/ECAM-01-2024-0134) 'This author accepted manuscript is deposited under a Creative Commons Attribution Noncommercial 4.0 International (CC BY-NC) licence. This means that anyone may distribute, adapt, and build upon the work for non-commercial purposes, subject to full attribution. If you wish to use this manuscript for commercial purposes, please [contact permissions@emerald.com](contact permissions@emerald.com).' Analyzing the differential impact of variables on the success of solicited and unsolicited private participation in infrastructure projects using machine learning techniques Muhammad Ayata, Mehran Ullahb, Zeeshan Pervezc, *Jonathan Lawrenced, Chang Wook Kange, Azmat Ullahf* 1. Lecturer, School of Computing, Engineering and Physical Sciences, University of the West of Scotland, United Kingdom 2. Lecturer, School of Business and Creative Industries, University of the West of Scotland, United Kingdom 3. Professor, Faculty of Science and Engineering, School of Engineering, Computing, and Mathematical Sciences, University of Wolverhampton, Wolverhampton, UK 4. Professor, School of Computing, Engineering and Physical Sciences, University of the West of Scotland, United Kingdom 5. Professor, Department of Industrial and Management Engineering, Hanyang University ERICA, South Korea 6. Assistant professor, International School of Huaqiao University, Quanzhou, P.R China Corresponding Authors Azmat Ullah Assistant professor, International School of Huaqiao University, Quanzhou, P.R China Email: [azmat_aries897@yahoo.com](azmat_aries897@yahoo.com) * Sadly, Jonathan Lawrence, passed away in July 2024. This work is a testament to his dedication and expertise Analyzing the differential impact of variables on the success of solicited and unsolicited private participation in infrastructure projects using machine learning techniques Abstract The study aims to examine the impact of key variables on the success of solicited and unsolicited private participation in infrastructure (PPI) projects using machine learning techniques. The data has information on 8,674 PPI projects primarily derived from the World Bank database. In the study, a machine learning framework has been used to highlight the variables important for solicited and unsolicited projects. The framework addresses the data-related challenges using imputation, oversampling, and standardization techniques. Further, it uses Random forest, Artificial neural network, and Logistics regression for classification and a group of diverse metrics for assessing the performances of these classifiers. The results show that around half of the variables similarly impact both solicited and unsolicited projects. However, some other important variables, particularly institutional factors, have different levels of impact on both types of projects, which have been previously ignored. This may explain the reason for higher failure rates of unsolicited projects. The study highlights this differential impact ofvariables for solicited and unsolicited projects, challenging the previously assumed uniformity of impact and providing specific inputs to investors, policymakers, and practitioners. Keywords: PPI projects, Solicited proposal, Unsolicited proposal, Critical success factors, Project contexts 1 Introduction PPI project is a commonly used style of public-private partnership in which the private sector participateson a contractual basis (Taguchi and Sunouchi, 2019a). Governments grant rights to private parties for the building and operation of a

FAQs

What is the main objective of the study?

To examine how key variables differentially affect the success of solicited versus unsolicited private participation in infrastructure (PPI) projects using machine learning.

What dataset does the study use?

The analysis uses information on 8,674 PPI projects, primarily derived from the World Bank database.

Which machine learning methods are used for classification and how are results evaluated?

The framework uses Random Forest, Artificial Neural Networks, and logistic regression, and it assesses classifier performance using a group of diverse metrics.

Aug 6, 2026

Upload by Olivia Brown