Smarter Tools for (Citi)Bike-Sharing
Talkat Optimization and Decision-Making Under Uncertainty (Simons Institute, September 2016) · 2016-09-19..09-23·
summary
City bike-share demand gets modeled as Poisson arrival/return rates per station, then time-sliced into half-hour periods and analyzed with a stochastic dynamic program to compute expected upset users (empty or full). Dock-and-bike allocation becomes a convex problem with an optimal greedy marginal-improvement algorithm provably optimal via multimodularity. Empirical results show reallocating dock capacities beats overnight truck rebalancing, trike-based midrush matchings improve service, and small incentive/pricing tweaks can shift usage patterns.
AI-written summary · about
chapters (21)
- 0:00Introduction
- 0:28What is BikeSharing
- 1:28Traffic in New York
- 4:01Data Management
- 4:45Performance Improvement
- 5:08Stochastic Modeling
- 5:55Cost Function
- 10:12The Power of wishful thinking
- 15:41Station allocation
- 15:59Behavior
- 17:44Problem
- 18:13Greedy Algorithm
- 19:26Multi Modularity
- 23:09Results
- 26:39Other Issues
- 27:33MidRush Rebalancing
- 28:21MidRush Optimization
- 29:06Pricing Plans
- 30:01Incentives
- 30:59Optimization
- 32:34Gaming
related talks
49mStructural estimation methods to model user behaviour in bike-sharing systems
21mPredicting Usage for Capital Bikeshare stations based upon Spatial Characteristics
06mUnderstanding User Behavior in Car Sharing Services Through The Lens of Mobility: Mixing ...
32mTour de Bikeshare: Setting World Records with JavaScript
31mScaling up Lyft’s Growth via Causal ML and Bandits
21m"Capacity Prediction" instead of "Capacity Planning":
06mA City-Wide Crowdsourcing Delivery System with Reinforcement Learning
28m"Where, When, Why, and How: Directi