Research map / Learning theory and algorithms / Combinatorial and search optimization
When Hashing Met Matching: Efficient Spatio-Temporal Search for Ridesharing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use spatio-temporal route representations with LSH instead of CLOSEBY-HAVERSINE candidate search | NY yellow taxi ride matching · Morning and evening commute, varying load | matching utility: about 6% higher | Helped |
| Use spatio-temporal route representations with LSH instead of CLOSEBY | NY yellow taxi ride matching · Morning and evening commute | matching utility | Helped |
| Use spatio-temporal route representations with LSH instead of HAVERSINE | NY yellow taxi ride matching · Morning and evening commute | matching utility | Helped |
| Use up to one additional alternate route when available (ablation) | LSH · NY yellow taxi commute | matching utility as fraction of optimal | Helped |
| Choose space discretization that is too coarse (ablation) | LSH · NY yellow taxi ride matching | matching utility | Hurt |
| Choose space discretization that is too fine (ablation) | LSH · NY yellow taxi ride matching | computation time | Hurt |
| Choose space discretization that is too fine (ablation) | LSH · NY yellow taxi ride matching | matching utility | Hurt |
| Use a large time-discretization interval (ablation) | LSH · NY yellow taxi ride matching | matching utility | Helped |
| Center ride vectors along each dimension before normalization (ablation) | LSH · NY yellow taxi ride matching | success probability | Helped |
| Increase the number of LSH tables (ablation) | LSH · Approximate potential match search | success probability | Helped |
| Increase the number of hash functions per table (ablation) | LSH · Approximate potential match search | success probability | Hurt |
| Use multi-probe queries (ablation) | LSH · Approximate potential match search | success probability | Helped |
Closest papers by meaning
- Online Spatio-Temporal Matching in Stochastic and Dynamic Domains (AAAI 2016 · similarity 0.86)
- Real-Time Driver-Request Assignment in Ridesourcing (AAAI 2022 · similarity 0.85)
- Stochastic Matching via Local Sparsification (NeurIPS 2026 · similarity 0.82)
- MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic (NeurIPS 2026 · similarity 0.81)
- Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems (NeurIPS 2025 · similarity 0.81)
- BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem (NeurIPS 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.