Fuzzy inference systems (FISs) are a predictive modeling technique based on fuzzy sets that utilize approximate reasoning to mimic the decision-making process of human experts. There are several expert- and data-driven methods for developing FISs, among which fuzzy clustering algorithms are the most frequently used data-driven methods. This paper introduces a new fuzzy clustering algorithm for developing FISs in construction applications that addresses two limitations of existing fuzzy clustering algorithms: the lack of capacity to determine the number of clusters automatically from the characteristics of the data, and the poor performance in predictive modeling of highly dimensional problems. Existing fuzzy clustering algorithms are limited in construction applications since determining the number of clusters based on subjective expert judgment reduces the accuracy of the resulting FIS, and construction systems are often highly dimensional with a large number of inputs affecting the system outputs. The fuzzy clustering algorithm proposed in this paper determines the number of clusters automatically based on the characteristics of the data, specifically the non-linearity observed within clusters, and assigns weights to the rules of FISs to improve their accuracy in highly dimensional problems. This paper advances the state-of-the-art of fuzzy clustering and contributes to construction modeling by providing a new data-driven technique for developing FISs that suits the characteristics of construction problems.