An urban legend says that a data science task is mainly finished after the development of models. The truth is that a much more important phase follows, often tougher than model development: managing and governing these ready-to-use models to keep your data science project relevant for the long haul. If you're a visual learner, you might prefer tuning into my Open Data Science Conference presentation, First Aid Kit for Data Science: Keeping Machine Learning Alive. In just over 24 minutes, I cover the machine-learning lifecycle, which includes finding the right data, preparing and exploring it and building, registering and reassigning models. I use a fraud detection project as an example.

Chris Hemedinger and Jared Dean describe how they used SAS Viya to build the topic recommendation engine for the SAS Support Communities. They discuss all phases of building a recommendation engine: data preparation, machine learning to build the analytical scoring model, the REST API to score topics for visitors, Docker and Kubernetes to host and scale the engine, and a DevOps approach to rebuild and redeploy the model each day with new data. Chris and Jared demonstrate the eclectic mix of SAS products and open source tools that they used, including SAS Visual Data Mining and Machine Learning, SAS Enterprise Guide, VS Code, Gitlab, Python, SAS Model Manager, Google Analytics, Apigee, Microsoft Teams, Docker, and Kubernetes. See the "Recommended by SAS" widget for yourself: visit https://communities.sas.com and sign in for personalized topic recommendations. Content Outline 01:09 – Demonstration of the live recommendation engine 03:05 – Data collection and preparation 04:37 – Python and SAS code (PROC FACTMAC) in Jupyter Notebook 08:04 – REST API built using Python Flask and SAS Micro Analytics Service 09:11 – DevOps infrastructure to deploy to production 11:30 – Calling the API from SAS Communities 13:01 – Monitoring APIs with Apigee and alerting with Microsoft Teams 15:19 – Google Analytics to track events, SAS Model Manager to predict success Additional Resources Building a recommendation engine with SAS - https://blogs.sas.com/content/sasdumm... Learn more about SAS machine learning APIs and developer tools SAS For Developers – https://developer.sas.com