Demand Forecasting and Rebalancing in Shared Bike Systems Using Deep Learning and Evolutionary Computation*
Bibliographic record
Abstract
Shared bikes offer an eco-friendly alternative to conventional public transport and can reduce traffic congestion. However, imbalances in bike availability at stations necessitate effective rebalancing strategies to prevent shortages or surpluses. Previous studies on shared bike rebalancing have mainly concentrated on station demand forecasting or route optimization. However, focusing only on demand forecasting does not effectively manage bike quantities at stations, and route optimization alone fails to address real-time demand fluctuations. This paper introduces a hybrid solution combining deep learning and evolutionary computing to tackle both demand forecasting and route optimization for rebalancing with multiple capacitated trucks. Station demand forecasting is modeled as a time series forecasting problem, and route optimization for bike rebalancing, guided by these forecasts, is addressed as a Capacitated Vehicle Routing Problem with Pickup and Delivery (CVRPPD). Deep learning is used to predict short-term demand at each station, which then informs the rebalancing strategy. Our objective is to optimize rebalancing routes to minimize both unmet station demand and carbon emissions from trucks. This involves selecting which stations each truck should visit. We use a Genetic Algorithm (GA) to identify the most efficient rebalancing routes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".