PHD Discussions Logo

Ask, Learn and Accelerate in your PhD Research

Question Icon Post Your Answer

Question Icon

4 months ago in Supply Chain Management By Babita

Are there publicly available supplier performance datasets for data mining?

I’m working on a data mining project related to supplier performance, but I’m struggling to find real-world datasets. Are there any publicly available supplier performance datasets that researchers can use, or do people usually create their own?

All Answers (2 Answers In All)

By Kunal Answered 2 months ago

Public, real-world supplier performance datasets are quite rare because this data is usually sensitive and proprietary. However, researchers can still find useful alternatives. Platforms like Kaggle (using keywords such as “supply chain” or “vendor”), the UCI Machine Learning Repository, and Data.World host related datasets. Some academic studies also share anonymized or synthetic data. If suitable data isn’t available, creating a synthetic dataset using KPIs like on-time delivery, quality acceptance rate, and lead-time variability is a practical and widely accepted approach.

Replied 2 months ago

By Babita

Thanks a lot! This is really helpful Kunal.

By Meera Answered 1 month ago

Another option is to look at procurement and supply chain datasets that include related metrics, even if they don’t label them specifically as “supplier performance.” For example, datasets on inventory levels, purchase orders, or shipping logs can be used to derive supplier KPIs like delivery timeliness or defect rates. Combining multiple datasets and cleaning them can effectively simulate a supplier performance dataset suitable for data mining experiments.

Your Answer