Global Energy Company Problem
A global energy company had several teams using disparate methods and resources to accomplish very similar tasks. One team had a data modeling pipeline for daily bidding predictions in a regional market. It failed three to five times per week, required daily manual uploads, lacked data validation, had no pipeline infrastructure, and algorithm modifications were difficult to test and implement.
Solution
OpenTeams’ Open Source Architects installed a data science platform (Nebari) that provided shared, scalable compute, and storage across all teams. They created a pipelining solution to demonstrate best practices in MLOps for all of their teams to adopt, including automated data ingest and validation, model training, and dashboards to reduce errors, provide monitoring, and make model experimentation easy.
Outcome
The outcome was an example of MLOps best practices for all of their teams to adopt. It reduces ETL and modeling errors and makes scaling, model experimentation, and production deployment easy.