Apart from the loss of time and money, disputes between public authority and private partner in China’s public-private partnership (PPP) projects are destroying the government’s image of PPP support and the private partner’s investment confidence. This article aims to explore the main causes for PPP disputes, present the results of disputes, and then predict the litigation outcomes. Based on 171 PPP litigation cases from China Judgements Online within 2013–2018, the research identified 17 legal factors and explained how these factors influence the litigation outcomes, which are named as “prediction approach” in this study. Nine machine learning (ML) models were trained and validated using the data from 171 cases. The ensemble model of gradient boosting decision tree (GBDT), k-nearest neighbor (KNN) and multi-layer perceptron neural network (MLP) performed best compared with other nine individual ML models, and obtained a prediction accuracy of 96.42%. This study adds meaningful insights to PPP dispute avoidance, such as high compensation of expected revenues could prevent the government from terminating the contract unilaterally. To some extent, if parties consider the case litigation outcome, they are more likely prefer a rational settlement out of court to avoid further aggravation of the dispute, and would also alleviate the pressure of litigation in China.

Disputes are inevitable in public-private partnership (PPP) projects and generate great losses of time and money in practice. If an in-depth understanding of dispute sources can be obtained beforehand, the process of PPP may become more smooth. This paper aims to identify and assess the causes of PPP disputes between the public and private sectors. First, 15 causes are explored based on the PPP litigation cases from China Judgments Online. Second, the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method is utilized to provide a holistic understanding of the relative importance and define the cause-effect categories among PPP dispute sources. The results demonstrate that the top three decisive causes of PPP disputes are the repudiation of contracts (result category), lack of expertise and experience (reason category), and unreasonable risk allocation (result category). Further, dispute avoiding strategies are proposed to minimize or completely avoid the occurrence of PPP disputes. The outputs are expected to add meaningful insights to potential sources of dispute and dispute prevention mechanisms in PPPs. To some extent, the investors can develop strategic measures through the findings before entering into PPP markets.

Disputes involved in public–private partnership (PPP) projects destroy the relationship between governments and private partners and generate huge losses. To multiply the chances of successfully preventing disputes, a holistic understanding of how a PPP dispute occurs is necessary. This paper contributes to the PPP dispute studies domain in (1) identifying various contributors that lead to the formation of PPP disputes at different levels, (2) proposing a fault tree (FT) framework of a PPP dispute, and (3) evaluating the likelihood of a PPP dispute and displaying the weakest part of a PPP project. First, three basic components that drive the development of PPP disputes are identified: project uncertainty, opportunistic behaviors, and contractual incompleteness. Second, scenario modeling of PPP disputes through fault tree analysis (FTA) depicts a more intelligible structure of PPP disputes. Furthermore, the fuzzy sets evaluation method was employed to compute the fuzzy occurrence likelihood of a PPP dispute. The results indicate that dispute is inevitable in PPP projects (with an occurrence likelihood of 0.9464). Additionally, opportunism is the dominant dispute inducer in PPPs. Our findings are expected to help PPP participants understand how various drivers contribute to the occurrence likelihood of PPP disputes where past data is inadequate. Then, more cost-efficient and appropriate preventive strategies can be developed based on the assessment to minimize the occurrence of PPP disputes.