Kalypso acquired by Rockwell Automation, Inc. (NYSE: ROK). Read the press release.

How AI automated spend classification at a consumer packaged goods company

Kalypso was engaged by an existing client to develop a solution for accurately classifying financial transactions. Our client was already familiar with the quality benefits of AI in their product development process, but this time they needed to turn the digital lens inward.

In any organization, tracking spend against cost centers or cost codes is an essential task. But for a large organization like our client’s, with more than 157k unclassified transactions, inconsistencies were high.

Our client found 74% of their purchase order transactions were missing an assigned cost code. The burden of correcting or re-classifying those transactions fell squarely on the shoulders of project managers.

By leveraging an ensemble of machine learning models, we were able to first process and bulk categorize past financial transactions, then clean error-filled and inconsistent fields to finally label the data into consistent categories.

At 99% accuracy, this data cleansing and classification pipeline allowed project managers to bypass the data clean-up work that would previously cost them hours of tedious labor to go directly to the value-add work of analyzing expenditure patterns.

Our work optimized spend classification, saved countless hours of manual effort and increased data consistency.

The same techniques leveraged to classify unstructured transaction data have already proven to be valuable across other areas of R&D where the presence of unstructured data was previously limiting opportunities for analytics and robust insights.

We helped our client continue their AI journey, delivering immediate value while building the framework for continual improvement in the future.

Thought Leaders

Jordan Reynolds 2018
Global Director, Data Science
Chelsea Barnes 2018