Model Parameters for Bike-Sharing Dynamic Pricing Optimization

Jianrong Cai published model parameters for a Dynamic pricing-based Stochastic Demand-Response Optimization (DSDRO) method on figshare in April 2026. The dataset supports a framework that uses spatiotemporal bike-sharing demand patterns to optimize pricing and resource allocation. Numerical experiments based on real operational data validated the approach.

Use Cases

• Benchmarking bike-sharing pricing algorithms based on the described DSDRO framework.
• Analyzing the impact of dynamic pricing on revenue based on the reported 300% increase.
• Evaluating rebalancing cost reduction strategies based on the 76.21% improvement from the LNS component.
• Testing optimization algorithm stability based on the reported coefficient of variation below 5%.

Strengths

• The proposed DSDRO method increased expected revenue by 15.51% and net profit by 24.18% in experiments.
• Dynamic pricing alone increased revenue by over 300% relative to fixed pricing.
• The Large-scale Neighborhood Search component reduced rebalancing cost by 76.21% relative to pure PSO.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is 9.5 KB, indicating a very limited scope of parameters.

Provenance

Source

Jianrong Cai

Collection Method

Likely derived from numerical experiments based on real bike-sharing operational data.

Freshness

Last updated 2026-04-16 17:40:08; freshness should be verified.