Help us improve the AWS re:Post Knowledge Center by sharing your feedback in a brief survey. Your input can influence how we create and update our content to better support your AWS journey.
Questions tagged with Amazon Personalize
Amazon Personalize enables developers to build applications with the same machine learning (ML) technology used by Amazon.com for real-time personalized recommendations – no ML expertise required.
Content language: English
Filter questions
Select tags to filter
Sort by
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
109 results
We are using Personalized-Ranking-v2 recipe for recommendations. We see a problem where the results seem stale. When you request the api for a userId, majority of the recommendations are repeated. Thi...
1
answers
0
votes
37
views
asked 2 months ago
Hi AWS team,
I need guidance on the correct setup and the recommended recipe for a use case where recommendations must differ per country, based purely on user interaction behavior — not on static it...
1
answers
0
votes
97
views
asked 5 months ago
Hi everyone,
I’m working on a use case involving Trending Now / popular items and Next Best Action in Amazon Personalize. I want the model to return different trending items per country, based purely...
1
answers
0
votes
99
views
asked 5 months ago
Hello,
I am not able to create recommendations for aws next best actions, I always receive 0.0 score.
Don't know what I am doing wrong because datasets looks good from my perspective.
Example data:...
1
answers
0
votes
93
views
asked 5 months ago
I am using a straightforward filter on top of my my aws-user-personalization-v2 solution:
`INCLUDE ItemID WHERE Interactions.event_type IN ("sent")`
When I request results for user XYZ using the "Tes...
1
answers
0
votes
114
views
asked 9 months ago
Hello AWS Community,
I'm currently utilizing Amazon Personalize and am **considering requesting an increase in the service quota for the number of active dataset groups from the default limit of 5 to...
5
answers
0
votes
182
views
asked a year ago
Hello,
Our items menu changes every 4 days, so the items datasets must be re-imported every 4 days, and therefore the interactions dataset will be changed (because we now have different items, we imp...
1
answers
0
votes
108
views
asked a year ago
Hello,
We can create a `Personalize Solution` using **CDK**, using this code (as an example)
```
personalize.CfnSolution(
self,
"FrequentlyBoughtTogetherSolution",
...
1
answers
0
votes
174
views
asked a year ago
This is a follow up from this post: https://repost.aws/questions/QU5QK9A7kLTfiYS_TKeq-gdQ/clarity-needed-for-sims-recommender-from-amazon-personalize
I am trying to understand the exact definition of...
0
answers
1
votes
76
views
asked a year ago
Hello, I have an issue with getting recs using POPULARITY_COUNT or TRENDING-NOW recipes. As part of our recommendation system, we get recs using user-personalization recipe for a promotion email campa...
1
answers
0
votes
139
views
asked a year ago
I need clarity for how the SIMS recipe works behind the scenes. I have read that SIMS finds similar items based on collaborative filtering. Can this be expanded on? When I give SIMS an item ID, what d...
1
answers
0
votes
151
views
asked a year ago
Hi Everyone,
I created a campaign using the `user_personalization_v2` recipe. Out of curiosity, I tested it by inputting fake user IDs like "Test" or "John Doe", which I confirmed do not exist in our...
1
answers
0
votes
148
views
asked a year ago