What is the difference between "Use Case Optimized Recommenders" and "Custom Recommender Solutions" in Amazon Personalize?

Question

I'm new to Amazon Personalize, I'm checking the price of this service on this link and I see 3 different categories ("Use Case Optimized Recommenders" "User Segmentation" and "Custom Recommender Solutions"). I wonder what the main difference between them is?

As I noticed, the Use Case Optimized Recommenders price doesn't include "Training cost" and "TPS cost". Is this true? How can this Recommendation Mode work without Training?

Also, what should I do if I upload new data from a new user and need to re-train each month? Can I do it in the Use Case Optimized Recommenders since they don't have "Training Cost"? Since the price from Custom Recommender Solutions for real-time recommendations is quite high.

Answer 1

Use Case Optimized Recommenders (UCOR) are easier to configure initially and also easier to maintain than Custom Recommender Solutions (CRS).

Let's compare them using the example of "Frecuently bought together", a UCOR and "aws-similar-items", a CRS.

For initial configuration, the CRS will ask you for hiperparameters like the number of hidden dimentions or backpropagation through time, while configuration for the UCOR is minimal.

In this example, you can also choose the Event Type to look for in the aws-similar-items. If you choose "Purchase", the aws-similar-items will work like the Frecuently bought together domain use case, but you have the liberty to choose any Event Type you want to focus on.

For this example, the UCOR automatically does a full retraining every 7 days, and an automatic update every 2 hours to consider new items. The CRS requires you to create a Campaign that will point to the last solution version, which must be retrained manually. You decide when to do a full retraining and when to update the solution to consider new items. This is why the CRS needs a campaign and the UCOR use case doesn't (solutions have many versions that need to be managed).

Both CRS and UCOR allow for real-time recommendations. They consider new interactions to update that particular users' preferences, but don't update the entire recommender to learn from this interaction. That only happens on full-retraining.

Now to answer your question:

Also, what should I do if I upload new data from a new user and need to re-train each month? Can I do it in the Use Case Optimized Recommenders since they don't have "Training Cost"? Since the price from Custom Recommender Solutions for real-time recommendations is quite high.

You would just upload the new user's data to the users' dataset and it would automatically retrain every 7 days. You don't have to manually do it, while in CRS, you would retrain manually and the campaign would then use that last solution version.

If by new user data you mean interactions, this will automatically be considered for that particular user if you uploaded it through the Event Tracker.

Answer 2

Training and retraining is managed by Personalize for Use Case Optimized Recommenders. They are designed specifically for the most common use cases in Media (VOD) and Retail and are intended to make it easier to launch and operate recommendation engines for these industries. They must be created within a Domain Dataset Group.

Domain dataset group: A dataset group containing preconfigured resources for different business domains and use cases. Amazon Personalize manages the life cycle of training models and deployment. When you create a Domain dataset group, you choose your business domain, import your data, and create recommenders for each of your use cases. You use your recommender in your application to get recommendations with the GetRecommendations operation.

Therefore, the cost for retraining Use Case Optimized Recommenders is built-into their pricing. There is still a cost for real-time recommenders when you exceed the free number of recommendations per hour.

Custom Recommenders do not support automatic training/retraining so you are responsible for initiating training by creating Solution Versions. Note that you can add custom recommenders to a domain dataset group but you cannot add use case optimized recommenders to a custom dataset group.

If you start with a Domain dataset group, you can still add custom resources such as solutions and solution versions trained with recipes for custom use cases.

Regardless of the dataset group type you create, you still want to keep your datasets updated with the latest interactions and item/user data.

User Segmentation is designed for building segments of users based on their affinity for items or item attributes. They are considered custom recommenders from a training/retraining perspective.

The AWS pricing calculator for Personalize was recently updated to support Use Case Optimized Recommenders and User Segmentation.