Bicycle sharing is a notable sustainable transporta-tion option for metropolitan regions and communities seeking to address environmental concerns, reduce traffic congestion, and combat air pollution while promoting public health and improving connections.There are already technologies to support this system, including typical mobile applications and kiosks strategically positioned at the bicycle station.Nevertheless, most proposed solutions cannot accurately forecast the demand for bicycle availability, efficiently redistribute bicycles, create routes to circumvent traffic congestion and conduct comprehensive user analysis.To address these challenges, a framework for an AI-enabled bicycle-sharing system has been presented to predict the count of bicycle rentals.To assess performance, four distinct ensemble-based models are implemented and tested using various statistical parameters.