Facebook IconFacebook IconFacebook IconFacebook Icon

Optimizing procurement with AI

Sagacify Logo


Managing procurement in a multinational company might be challenging. Arcelor Mittal was searching for a solution to centralize their procurement operations over different divisions of the company. Working closely with our client, we built a customized AI solution for their problem.


Optimize procurement

Until today, different divisions of Arcelor Mittal would order identical products separately from one another, which led to lost opportunities. Indeed, if they would have ordered these products together, they could have negotiated a better deal. However, this was not possible, since their procurement operations lacked a system that would spot similar and regroup orders (product orders of identical manufacturers and/or references).

Sagacify brought a solution to this problem with its AI expertise. For this project, we applied NER (Named Entity Recognition) algorithms to extract and structure the manufacturers and ordered product references in the text descriptions. We also used active learning to optimize the labeling of the dataset.


Streamlined operations

Positive results were obtained as duplicates were accurate and have been proven useful for Arcelor Mittal to optimize its operations. This project allowed Arcelor Mittal to successfully optimize orders between its different divisions and generate substantial benefits for them.

Related cases