Urbanization increases runoff, sediment, and nutrient loadings to freshwaters, causing flooding, harmful algal blooms, and increased costs for drinking water filtration. Most watershed models use runoff quality data from specific land uses; coupled with a variety of methods for quantifying loads, the most common being Build-up and Wash-off (BUWO) equations for which loading is a function of antecedent dry period (ADP). However, several studies have shown there is no significant correlation between urban runoff quality and ADP, suggesting predictions based solely on landuse and ADP are questionable. The objective of this study is to discover which parameters, climatological or catchment characteristics, are most significant and should be included in the BUWO relationship. Stormwater quality data was obtained from the National Stormwater Quality Database (NSQD), which is the largest and most recent database of its type in the U.S. Bayesian Network Structure Learner (BNSL) was used to assess the relationships between catchment characteristics, climatological information, and runoff quality for each land use. Given the optimal BN structure, it was determined which parameters affect water quality event mean concentrations the most, and which the least. The results demonstrated that for some constituents (i.e. particulate nitrogen, particulate phosphorous, and sediments), other factors (such as rainfall depth and duration, surface slope) exert a more important influence on urban runoff quality than ADP.