Design an ML Recommendation Engine

Design an ML Recommendation Engine | System Design

День тому

Visit Our Website: interviewpen.com/?...
Join Our Discord (24/7 help): / discord
Like & Subscribe: / @interviewpen
Tons of modern software services, such as social media and ecommerce, include systems for recommending content to users. This video dives into the details of how to deploy a machine learning algorithm at scale for recommendations, and discusses how these systems are trained and used on a recurring basis.
If you liked this video and want to learn more about fundamental systems and how they can be used to solve problems, check out our full course on interviewpen.com/?... !
Table of Contents:
0:00 - Introduction
0:43 - ML Inputs and Outputs
2:07 - Training
2:58 - Training: Tracking Server
3:47 - Training: Incremental
5:05 - Training: Workflow Orchestration
6:01 - Inference: API
6:40 - Inference: Caching
8:03 - Next Steps
Socials:
Twitter: / interviewpen
LinkedIn: / interviewpen
Website: interviewpen.com/?...

КОМЕНТАРІ: 13

@shreyas2k15 21 день тому

These are incredibly well made and well articulated videos. Thank you!

@interviewpen 18 днів тому

Thanks!

@alirezakhorami 16 днів тому

Amazing job, I love your videos about data, keep rocking

@interviewpen 14 днів тому

Thank you!

@RiwenX 22 дні тому

So you have to retrain the model for each new user?

@JohnSmith-op7ls 21 день тому

You can train a model to simply correlate various demographic attributes to liking certain things, then it can guess based on new user demographics. You can get more elaborate and first try to find if there are strong correlations between cohorts of certain baskets of demographics, then use that, alone or in combination with individual demographic attributes. Basically you have to run the numbers to see what produces the best recommendations. You wouldn’t have nearly enough data on new users to be statistically relevant in a data set large enough to itself be statistically relevant. Over time you’d want to,retrain the model as enough new data on new and existing users is added. Otherwise the model’s accuracy can drift.

@interviewpen 18 днів тому

Not necessarily--the model can still make guesses based on the behaviors of other users along with whatever data you feed it during inference. However updating the model with a user's past behaviors will increase accuracy. Hope that helps!