Quantitative approaches to estimating user demand provide a powerful tool for engineering designers. We hypothesized that estimating binomial distribution parameters n (user population size) and p (user population product affinity) from historical user data can predict demand in new situations. This approach applied to a major Bike Sharing System (BSS) expansion. BSS Operators must make key decisions when adding additional docking stations. Binomial Parameter estimation approaches are briefly discussed, followed by evidence that BSSs supply an amiable case for parameter estimation. Parameter plots reveal a continuous surface over the BSS area. These surfaces allow prediction of overall ridership levels at new station locations distinctly and more accurately from approaches currently utilized. Utilizing spearman’s Rho as a comparison benchmark, our approach yields a stronger correlation between our prediction and the observed new station utilization (rho = .830, stations = 46, p < .01) than the order implemented by the BSS operator (rho = .596, stations = 46, p < .01). Finally, this approach is mathematically straightforward, indicating potential as a mainstream BSS tool for BSS operators planning future station expansions. The results validate our approach of using current user data to determine target population characteristics, informing decisions about new design situations.
Binomial Parameter Determination and Mapping for Demand Prediction: A Case Study of Bike Sharing Station Expansion Design
- Views Icon Views
- Share Icon Share
- Search Site
Watson, BC, & Telenko, C. "Binomial Parameter Determination and Mapping for Demand Prediction: A Case Study of Bike Sharing Station Expansion Design." Proceedings of the ASME 2018 International Mechanical Engineering Congress and Exposition. Volume 13: Design, Reliability, Safety, and Risk. Pittsburgh, Pennsylvania, USA. November 9–15, 2018. V013T05A066. ASME. https://doi.org/10.1115/IMECE2018-87865
Download citation file: