Effective pavement management systems are essential for accurately predicting pavement conditions and efficiently planning and scheduling maintenance, rehabilitation, and reconstruction activities. Significant efforts are dedicated to developing accurate pavement condition prediction models using machine learning (ML) at the state level. Conversely, insufficient investment, poor quality, and large variations in local roads data have resulted in less attention to modeling local pavement conditions. This study develops eight Bayesian-optimized single-estimator and ensemble ML classification models to predict local pavement roughness. Moreover, the classification granularity of pavement condition was investigated to assess its impact on the predictive power of various ML models. The results reveal that ML classification models with fewer classes exhibit higher accuracy and more stability in precision over recall values, in contrast to models with larger number of classes. The ensemble ML models surpass their single-estimator counterparts, with the category boosting algorithm demonstrating the highest performance, achieving testing accuracies of 0.77 and 0.65 for the three-level and five-level classifications, respectively. Hence, it is recommended to employ ensemble ML algorithms and a smaller number of classes to develop reliable, accurate, and stable predictive models for local roads with imbalanced condition data. This research helps transportation agencies improve their pavement condition prediction, thereby optimizing pavement management and resource allocation.