Bike-Repositioning Using Volunteers: Crowd Sourcing with Choice Restriction

Authors: Jinjia Huang, Mabel C. Chou, Chung-Piaw Teo11844-11852

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also develop a comprehensive simulation model using a threshold-based policy to deploy the volunteers in real time, to test the effect of choice restriction on volunteers (suitably deployed) to re-position bikes. We use the Hubway system in Boston (with 60 stations) to demonstrate that using a sparse structure to concentrate the re-balancing activities of the volunteers, instead of allowing all admissible flows in the system (as in current practice), can reduce the number of re-balancing moves by a huge amount, losing only a small proportion of demand satisfied.
Researcher Affiliation Academia Jinjia Huang, Mabel C. Chou, Chung-Piaw Teo Institute of Operations Research and Analytics, National University of Singapore, Singapore oraahj@nus.edu.sg, bizchoum@nus.edu.sg, bizteocp@nus.edu.sg
Pseudocode Yes Algorithm 1: State-dependent Empty Bike Re-balancing Policy
Open Source Code No The paper does not contain any explicit statement about making its source code available or provide a link to a code repository.
Open Datasets No The paper mentions using "the Boston Hubway system" data and refers to a "technical appendix" for data preparation, but it does not provide a concrete link, DOI, or formal citation for accessing this specific dataset publicly within the paper's text.
Dataset Splits No The paper mentions using "50-day output as training data (i.e., in-sample)" and "test our online re-balancing algorithm over another new 100-day simulation," indicating a train/test split. However, it does not explicitly mention a separate 'validation' dataset or its split details.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments or simulations.
Software Dependencies No The paper mentions using "SDPNAL+ solver developed by (Yang, Sun, and Toh 2015)" but does not specify a version number for this software, which is required for reproducibility.
Experiment Setup Yes We set the homogeneous volunteer arrival rate for each station to be c max{λ(v) i , i S}, where c is 0.05 (around 175 volunteers) or 0.1 (around 349 volunteers). The outside option O varies from 0 to 10 with step size 1.