In this study, type-1 fuzzy c-means and its interval and general type-2 versions were applied to a digital capability-based synthetic data. The synthetic data were generated via a Monte Carlo method under multivariate normality parameterized by an empirical mean vector and a shrunk covariance matrix. The performances of type-1 and type-2 fuzzy clustering algorithms were evaluated using a cluster validity index and discriminant analysis. Kim and Ramakrishna’s validity index was utilized to determine the optimal fuzzy partitions of the synthetic data. The synthetic data was partitioned into three fuzzy clusters. Discriminant analysis was conducted to assess the separability of the obtained fuzzy clusters. Consequently, the type-1, interval type-2, and general type-2 fuzzy clustering algorithms achieved the highest group case proportions under “Small”, “Medium”, and “High” fuzzifier settings, respectively.