SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks

Overview

• Name: SupplyGraph
• Task Category: Graph‑ML
• Language: English (en)
• Tags: finance, supply chain
• Data Scale: Less than 1K (n<1K)
• License: MIT

Authors

• Azmine Toushik Wasi
• MD Shafikul Islam
• Adipto Raihan Akib

Affiliated Institution

• Computational Intelligence and Operations Lab - CIOL, SUST

Dataset Description

• Source: From a leading FMCG company in Bangladesh.
• Purpose: For production purposes in supply‑chain planning.
• Characteristics: Contains temporal data as node features for sales forecasting, production planning, and factory problem identification.
• Goal: By using this dataset, researchers can leverage Graph Neural Networks (GNNs) to solve multiple supply‑chain problems, fostering development in supply‑chain analysis and planning.

Citation

@inproceedings{supplymap2023wasi, title={SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks}, author={Azmine Toushik Wasi and MD Shafikul Islam and Adipto Raihan Akib}, year={2023}, booktitle={4th workshop on Graphs and more Complex structures for Learning and Reasoning, 38th Annual AAAI Conference on Artificial Intelligence}, url={https://github.com/CIOL-SUST/SupplyGraph/}, doi={10.48550/arXiv.2401.15299} }

or, @misc{wasi2024supplygraph, title={SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks}, author={Azmine Toushik Wasi and MD Shafikul Islam and Adipto Raihan Akib}, year={2024}, eprint={2401.15299}, archivePrefix={arXiv}, primaryClass={cs.LG} }