AI categorization tool

Reference number
Coordinator DECIMALEN AB
Funding from Vinnova SEK 500 000
Project duration October 2019 - September 2020
Status Ongoing
Venture AI - competence, capacity and capability
Call Start your AI journey!

Purpose and goal

The purpose of the project is to: -Improve the implementation of category purchase management in the public sector by making it easier and faster in order for the organisations to be able to make optimal purchases and thereby achieve great savings The aim of the project is to: -Develop a digital categorization tool where public organisations can categorize their purchasing data according to UNSPSC or CPV code system

Expected results and effects

Expected effects - The public sector should be able to categorize their purchases and, in this way, optimize purchases according to their real need. Something that will free up tax assets and not least affect the work on sustainability positively. Expected results - When uploading, data in the system should be able to check, by matching existing data of either product name or assigned UNSPSC or both and categorize the input data under the correct category and upper category. Finally, an Excel-compatible file should be able to be downloaded with the new categorized data.

Planned approach and implementation

The project contains five (5) work steps divided into several sub-moments. - Start-up and validation of data - Development of algorithms and ML - ML in process where the system is to be learned from the data and the code systems - Implementation of the AI solution in a Cloud-based service - Evaluation and accounting The implementation of the project will be done in close cooperation with an IT supplier who has solid experience in AI and ML. The assignment includes verifying both code and model based on current legal rules and ethical standards.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 23 September 2019

Reference number 2019-03368

Page statistics