The Medical Export Group (MEG)
Extracting product characteristics from text
MEG is a pharmaceutical wholesale organization that supports governments, NGOs, and aid organizations in responding to medical emergencies and improving access to quality health care. They do this by providing medicine and medical and laboratory equipment, including installation and training.
The challenge
MEG’s ambition was to speed up the sales process (customer request to final quote) by making their extensive product inventory more organized and transparent. The sales process could take up to 2 weeks due to the size and product preferences of the request, whereas MEG would like to give the customer a relevant offer right away. An obstacle to this was that product features (such as drug type, quantity, price) were in one variable, namely the product description. This got in the way of item findability and readability.
What we did
We embarked on a Natural Language Processing (NLP) project exploring whether product properties could be extracted from the product description. If possible, the product properties would then be added to the dataset, which would improve product findability.
The result
We delivered a script that extracts various product properties from the product description. The results were then added to the existing data set, which in combination with the database’s search filters significantly increased the findability of articles. Also, during the project interesting connections were found within the datasets that proved to be of great value outside the project. Also, documentation on the development of the NLP model, the choices made and reasoning within it, and valuable next steps were defined.
Test your own data maturity
Test your own data maturity
Your data maturity determines the results you can get from your data. How ‘data mature’ are you? By knowing where you stand, you can better assess what is the logical first step. Can’t figure this out by yourself? We are happy to help you discover it via our free online quick scan.
Wondering where your company stands? Take the online quick scan here!
Why collaborate with JADS MKB Datalab?
The JADS MKB Datalab supports Dutch SMEs that want to make the transition to a more data-driven way of working. The JADS MKB Datalab carries out projects with SME entrepreneurs and Data Science students. In addition, they offer several tools to help you define a Data Science project with impact, such as workshops, a Data Maturity Scan and a Data Project Canvas.
So, if you want to take on a specifically designed short-term data science project for your SME with a JADS MSc student, visit the JADS MKB Datalab Website. 150 SMEs have already participated!