Understanding User Behavior in Car Sharing Services Through The Lens of Mobility: Mixing ...
summary
Study combines an 185-participant survey with a year of operational logs covering 68,000 users 587,850 records from Beijing and comparative data from Fuzhou and Lanzhou to report concrete findings: about 50% of trips last ≤5 hours, ~70% of users visit no more than two stations, ~90% of users are aged 18–38, pickups concentrate in CBD and IT clusters, female users show more stable destinations, and temporal patterns vary by weekday/weekend. A behavior-aware BeXGBoost model is built for usage prediction and outperforms baselines for station deployment and rebalancing.
AI-written summary · about
related talks
49mStructural estimation methods to model user behaviour in bike-sharing systems
36mSmarter Tools for (Citi)Bike-Sharing
57mSmarter Tools for (Citi)Bike-Sharing
21mPredicting Usage for Capital Bikeshare stations based upon Spatial Characteristics
34mData Drives Business
06mData-Driven Battery-Lifetime-Aware Scheduling for Electric Bus Fleets
41mAnalysing and predicting inner-city parking space occupancy
06mCellPred: A Behavior-aware Scheme for Cellular Data Usage Prediction