Machine Learning-Driven Model to Analyze Particular Conditions of Contracts: A Multifunctional and Risk Perspective

Contracts can serve three functions-Control, Coordination, and Adaptation-to mitigate different risks. This multifunctional perspective based on the development of contract theory has been introduced in construction industries to analyze how general conditions of contracts deal with risks. However, the particular conditions of contracts present specific requirements closely related to projects, which can generate additional risks for both parties. To fill in the gap, this study analyzes nine particular conditions from nine projects with good performance respectively based on the Federation Internationale Des Ingenieurs-Conseils (FIDIC) 1999 Silver Book and explores what aspects good particular conditions focus more on to avert risks when modifying the general conditions. We built machine learning-based classification models to conduct a content analysis of complete contracts (containing both general conditions and particular conditions) to measure the functions of contracts. The optimal model was proved to be acceptable and then used for efficiently coding more particular conditions of the FIDIC 1999 Silver Book. The results indicate that good particular conditions roughly follow the functional distribution of general conditions and no significant difference is found in functional distribution between a whole complete contract and its underlying general conditions. It also suggests minor revisions should be made to the Adaptation function, and particular conditions should concentrate more on explicitly illustrating both parties' obligations and tasks prudently to mitigate potential risks. These findings can practically assist contract managers to analyze particular conditions and identify the potential risks.