In recent years, bike-sharing programs have become more prevalent. Bicycle usage can be affected by different factors, such as nearby events, road closures, and on-campus traffic policies. The research presented here analyzed the effect of weather (average temperature, total daily precipitation, average wind speed, and weather outlook), day of the week, holiday/workday, month, and season on the use of the Great Rides Bike Share program in Fargo, North Dakota, U.S.A. This study also focused on predicting the 2016 rental demand for the Great Rides Bike Share program using Bayesian methods and decision trees. Further, the order of importance among the causal attributes was assessed. It was found that decision trees worked well to predict the 2016 demand.