Equity Promotion in Public Transportation

Authors: Anik Pramanik, Pan Xu, Yifan Xu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Additionally, we test our algorithm against a few baselines on real data assembled by outsourcing multiple public datasets collected in the city of Chicago. Experimental results confirm our theoretical predictions and demonstrate the effectiveness of our LP-based strategy in promoting social equity, especially when the budget is insufficient.
Researcher Affiliation Academia 1 Department of Computer Science, New Jersey Institute of Technology, Newark, USA 2 School of Cyber Science and Engineering, Southeast University, Nanjing, China
Pseudocode Yes Algorithm 1: A Randomized Allocation Strategy (RAS) for Equity Promotion in Public Transportation.
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the methodology is available.
Open Datasets Yes We identify a total number of 17,875 target households based on data from the Chicago Metropolitan Agency for Planning (CMAP 2019) and the public transportation data by the Chicago Data Portal (CDP 2022). For each needy household, we set a poverty level following the guideline based on the income level estimation information provided by the Department of Health and Human Services (ASPE 2022). We assign each household a random race following the distribution recorded by the official US Census in Chicago, 2022 (Review 2022).
Dataset Splits No The paper mentions separating households into three groups based on poverty level but does not specify any train/validation/test splits (e.g., percentages or absolute counts) for reproducibility.
Hardware Specification Yes All experiments are conducted on a PC with 2GHz Quad-Core Intel Core i7 processor and 8GB main memory.
Software Dependencies No The paper mentions solving a Linear Program (LP) but does not provide specific version numbers for any software, libraries, or solvers used (e.g., specific LP solver, programming language versions, or libraries).
Experiment Setup Yes We set the subsidy in the ride-hailing program as $10, $15, and $20 per ride for Group Level 1, 2, and 3, respectively. For each bus route, we set the operating expense per vehicle revenue hour to $140. In our experiments, we aim to make a plan for one quarter with a total of budget of B {5, 7.5, 10, ..., 20} (million dollars).