BookmarkSubscribeRSS Feed

Building a recommendation engine with SAS

Started ‎12-18-2018 by
Modified ‎10-27-2021 by
Views 11,724

If you visit a discussion topic while signed in on the SAS Support Communities, then you've experienced a little bit of AI at work from SAS.

 

recommendwidget.png

 

We've recently unveiled a content recommendation engine, built using SAS analytics and model management technologies that are part of SAS Viya.  You can learn more about how we built this engine by watching this interview with @Jared, a Principal Data Scientist at SAS. (Click the maximize view icon in the video thumbnail to see the full detail.)

 

 

How "personal" are these recommendations?  Think of these as suggestions for "topics to explore."  The analytical model scores your viewing history against thousands of topics and hundreds of thousands of other users.  The result: topics that people "like you" have viewed, but that you have not seen yet (or in a while).

 

This live engine is a perfect example of the Analytics Life Cycle in action, including:

  • Data collection and preparation
  • Model development using machine learning algorithms (FACTMAC, or factorization machines, in this case)
  • Packaging the model in an analytics store (ASTORE) and wrapping in an API
  • Deploying the model and API in a lightweight Docker container, and orchestrating in Kubernetes
  • Provisioning access to the API using Apigee, an API gateway
  • Monitoring performance of the engine using Apigee, adding collaboration/alerting with Microsoft Teams
  • Collecting performance data about click-throughs, and feeding that back into a SAS Model Manager project to forecast and improve the algorithm.

Building the engine from data to deploymentBuilding the engine from data to deployment

More details and screenshots are available in this article at blogs.sas.com.

 

It's a great case study for how raw data combined with SAS analytics can result in a benefit, such as an improved visitor experience.  Well, at least we hope it's an improved experience.  Will the recommended topics be helpful to you, or at least interesting? We're interested to hear what you think.

Comments

SAS using SAS...excellent!

I'm curious to understand why my recommendations contain only year 2006 posts. 

@SASKiwi - Well, me too! @Jared has a list of refinements that he's looking into...including adding a "decay" factor for older topics.

@SASKiwi, As of January 7th I have a new decay scheme to favor more recent articles. Your recommendations appear to be much more recent. Can you look and tell me what you think?

 

Jared

Yikes...it recommended this 14-year-old post to me just now...

 

SAS Drug Development BOF at SUGI

There will be a BOF (Birds-of-a-Feather) session to talk about SAS Drug Development at 6:30pm on Monday in Room 2016 in Moscone West.

@tomrvincent Hope to see you there!

 

Actually, good to know.  I should filter out some older posts as candidates for recommendation.

Initial entry to community posting: interesting to see a base post of this sort, and my comn correcting itself from a continual hack of my address.

THANKS

My recommendations were all in Korean. Better brush up on my Korean language skills.....

@gw2021, That is very curious. Are you located in Asia? Welcome to SAS Communities I see you joined a couple of weeks ago so it may be a small data problem.

 

Jared

You should definitely post more on such topic

I like it; the information is valuable and exciting. Thanks for sharing! I hope you'll post more.

I'm trying to discover the field of recommendation engines and how it can influence my eCommerce plan. I mostly rely on sources and articles like https://variety.com/2020/digital/news/vody-stylehaul-stephanie-horbaczewski-jeremy-houghton-12348141.... I like the video you shared for simplicity; it helped me to learn few more things. Now I'm closer to creating my eCommerce site. If you have more interesting things and facts to tell - I would appreciate it

Not sure that this gives me a lot of confidence in SAS AI ... 3 of the 4 recommendations SAS AI gave me had titles in Korean (that I can't read). I clicked one of the links and the page was also in Korean (with no 'translate' button or anything). So, why is SAS AI recommending pages that are in Korean-only to me? Here's a screen-capture:

 

sas_ai_korean.png

 

 

Version history
Last update:
‎10-27-2021 03:46 PM
Updated by:

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

Free course: Data Literacy Essentials

Data Literacy is for all, even absolute beginners. Jump on board with this free e-learning  and boost your career prospects.

Get Started

Article Tags