AI-Based Vendor Spend Classification for Indirect Procurement

Actions Taken

·      Implemented an AI-based spendclassification framework using text analytics and neural network–basedmodels.

·      Designed training, scoring, and feedbackloops to continuously improve classification accuracy.

·      Applied hierarchical classification logic tohandle diverse and unstructured vendor descriptions.

·      Leveraged semantic understanding capabilitiesto interpret free-text procurement data.

‍

Outcomes Achieved

·      Achieved 90–95% classification accuracyon business-validated data samples.

·      Improved reliability of spend reportingacross services and indirect materials.

·      Increased operational efficiency within theglobal procurement organization.

·      Enabled more accurate budgeting andaccounting through consistent vendor classification.

‍