How Do I Start My ModelOps Journey with SAS® Model Manager. Q&A, Slides, and On-Demand Recording
How Do I Start My ModelOps Journey with SAS® Model Manager. Q&A, Slides, and On-Demand Recording
Watch this Ask the Expert session to learn how to put your SAS and open source models into action using SAS Model Manager..
Join Diana Shaw as she teaches you how to use SAS Model Manager to store and manage all types of models within one common model repository and organize them within projects and folders. You can also evaluate models for champion model selection, monitor performance, and publish models. Users have a variety of options to interact with SAS Model Manager from the web application, a REST API, SAS code or Python packages available on GitHub. During this webinar you will learn:
- How SAS Model Manager can unite all types of users in their ModelOps journey to support analytical model deployment and management.
- How embedded AI and machine learning are used in SAS Model Manager.
- How continuous integration/continuous delivery (CI/CD) is used in SAS Model Manager.
The questions from the Q&A segment held at the end of the webinar are listed below and the slides from the webinar are attached.
What value is SAS Model Manager generating for customers?
Rapidly deploying models to real-time, edge, and batch scoring applications. For instance, one customer is using SAS Model Manager to productionalize over 100+ models per day for use in the real-time alert notification for their manufacturing process. Another customer leverages SAS Model Manager output to reoptimize their production settings using nightly batch processing. SAS Model Manager is largely used by Banks, Financial Services, Telco, and Retailers for managing A/B testing and suggesting the best offer.
What types of businesses are using SAS Model Manager?
Banking, Financial Services, Telecom, IT Hosting Services, Manufacturing, Electronics Manufacturing, IT Technology, Automotive, Retailers, Government Agencies, and Consulting Firms. Essentially SAS customers have more than 100 models in production are often SAS Model Manager customers.
What SAS and open-source products are natively integrated into SAS Model Manager?
All SAS products (Visual Analytics, Model Studio, Enterprise Miner, Credit Scoring, SAS Studio, Intelligent Decisioning, Event Stream Processing, and others) are natively integrated. Upcoming SAS solutions like SAS Model Risk Management and SAS Risk Solutions are all planning to be natively integrated using SAS Model Manager as the ModelOps framework. SAS Model Manager is fully integrated with SAS 9.4 technology.
SAS Model Manager natively integrates Python and R models and can deploy SAS and open-source models to batch, real-time, and containers for storing and reporting. SAS Model Manager works with the users existing Python and R distributions. We have this all documented and it’s very customizable.
Within this framework using SAS Viya, how do people manage different runtime needs for different models? Ex. different versions of Python, different package configurations, etc.
SAS Model Manager’s Model Publish service automatically formats model execution code based on the desired deployment destination. Users can provide and specify different open-source distributions and supporting assets. We have this all documented and it’s very customizable. Additionally, users can also create model execution code that supports databases and restful endpoints.
Recommended Resources
PZMM (Python Zip Model Management
Want more tips? Be sure to subscribe to the Ask the Expert board to receive follow up Q&A, slides and recordings from other SAS Ask the Expert webinars.
