What is Bailo?

The aim of the Bailo service is to provide a consistent, managed ecosystem of machine learning models that may be deployed in a standardised and well orchestrated way. This will help to make greater use of ML models in operational contexts, and do so in a well controlled and low risk manner.

In particular the objectives of the service include:

• Providing a centralised repository of ML models, where possible with models in standard formats
• Enabling users to find existing ML models, encouraging re-use of best practice and avoiding duplication of work
• Preparing models for deployment in a standard way
• Ensuring any deployed models are fully compliant, and that compliance rules are applied consistently from a single service
• Providing standardised monitoring approaches for operational ML models in order to identify issues and improvement opportunities.

All of this documentation is available on our GitHub repository. Corrections and additions welcome.