Preference-Aware Task Assignment in On-Demand Taxi Dispatching: An Online Stable Matching Approach
Authors: Boming Zhao, Pan Xu, Yexuan Shi, Yongxin Tong, Zimu Zhou, Yuxiang Zeng2245-2252
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Evaluations on both synthetic and real datasets confirm our theoretical analysis and demonstrate that LP-ALG strictly dominates all the baselines on both objectives when tasks notably outnumber workers. |
| Researcher Affiliation | Academia | 1BDBC, SKLSDE Lab, Beihang University, China 2University of Maryland, College Park, USA 3ETH Zurich, Zurich, Switzerland 4The Hong Kong University of Science and Technology, Hong Kong SAR, China |
| Pseudocode | Yes | Algorithm 1: A simple LP-based non-adaptive algorithm: LP-ALG; Algorithm 2: A Natural Baseline: Greedy |
| Open Source Code | No | The paper does not include any explicit statement about releasing the source code for their methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | The real dataset is collected through the GAIA initiative, hosted by Didi Chuxing. |
| Dataset Splits | No | The paper mentions using the first 20 days for training and the remaining 10 days for testing, but does not explicitly mention a separate validation split for hyperparameter tuning or model selection. |
| Hardware Specification | Yes | The LP program is solved via the Glop Linear Solver on a PC with Intel(R) Core(TM) i7-7700HQ 2.80GHz processor and 16GB Memory. |
| Software Dependencies | No | The paper mentions using the 'Glop Linear Solver' but does not specify its version number or any other software dependencies with version information. |
| Experiment Setup | No | The paper describes how the dataset was constructed (e.g., discretizing the map, creating task types, sampling drivers, defining profits and distances) and the overall experimental methodology, but it does not provide specific hyperparameters or training configurations (e.g., learning rate, batch size, number of epochs) for the LP-ALG or baseline algorithms, nor for the Lin UOTD model used for arrival rate prediction. |