Questions tagged [amazon-personalize]

Amazon Personalize is a machine learning service that allows developers to add individualized recommendations to customers who use their applications. You can use Amazon Personalize in a variety of scenarios, such as giving users recommendations based on their preferences and behavior, personalized re-ranking of search results, and personalizing content for emails and notifications.

See: Amazon Personalize documentation

92 questions
0
votes
1 answer

How to change an dataset schema without deleting dataset and having to remove filters on Personalize?

I noticed that one of my schema fields that I need to filter on is a booleaN and as you can't filter on a boolean I need to change the schema. I was able to create a new schema using the new Python SDK but can't see how I can update the schema? You…
devnotdev
  • 85
  • 8
0
votes
1 answer

Similar-Items recipe shows mostly popular items, doesn't seem to use item metadata

With the introduction of the new aws-similar-items recipe I thought this would bring a big improvement to the "because you watched x" but for a lot of the items it seems to just show popular items, with items not even having any…
devnotdev
  • 85
  • 8
0
votes
1 answer

Aws personalize get most buying products

I want to get the most buying products of a user in the history. I'm currently using USER_PERSONALIZATION recipe, but GetRecommendations always returns wrong result. Please help. This is my interaction data for the user id:…
Dao Tam
  • 503
  • 1
  • 3
  • 13
0
votes
1 answer

AWS personalize: filtering all items already interacted with does not seem to persist

We're using AWS Personalize to get a personalized ranking of various items in our feed for a specific user. We are also using a filter that looks like EXCLUDE ItemID WHERE Interactions.event_type IN ("*") This filter is taken from an AWS blog that…
fpghost
  • 2,834
  • 4
  • 32
  • 61
0
votes
1 answer

SQL - Guarantee at least n unique users with 2 appearances each in query

I'm working with AWS Personalize and one of the service Quotas is to have "At least 1000 records containing a min of 25 unique users with at least 2 records each", I know my raw data has those numbers but I'm trying to find a way to guarantee that…
0
votes
1 answer

Filter amazon personalize availability based on a date range and stock on hand ( nullable value )

I have around 500K items whose availability depends on the stock on hand and the availability date( available_on and discontinue_on ). I want to filter unavailable items from the recommendation, I expect something like this: Include…
channa ly
  • 9,479
  • 14
  • 53
  • 86
0
votes
1 answer

How can I watch for an AWS Personalize status change?

Is there any way I could watch for any AWS Personalize status change? For example I have a Lambda function creating a Dataset Import Job, and I would like to trigger another action once this job is finished but I cannot find a way to "listen" to…
Pingolin
  • 3,161
  • 6
  • 25
  • 40
0
votes
1 answer

Any way to tell AWS personalize that some interactions count more than others?

I would like to train AWS personalize based on a bunch of different interaction types, for examples "list view", "detail view", "save", "click". Some interactions clearly mean more than others...for example if a user saves an item he presumably…
fpghost
  • 2,834
  • 4
  • 32
  • 61
0
votes
1 answer

How to expose AWS Personlize recommendations via REST API

I want to expose the recommendations from AWS Personalize to clients via REST API. At this point I am thinking about AWS API Gateway > AWS Lambda > AWS Personalise. Is there a native way to do this or a better approach to do this?
Mithun Manohar
  • 516
  • 1
  • 6
  • 18
0
votes
1 answer

InvalidInputException: AWS Personalize error importing boolean fields in user or item metadata

I'm building recommender system using AWS Personalize. User-personalization recipe has 3 dataset inputs: interactions, user_metadata and item_metadata. I am having trouble importing user metadata which contains boolean field. I created the following…
0
votes
1 answer

How to solve Multi_vendor problem in AWS personalize?

I am using AWS personalize for making a recommendation system, specifically SIMS model (item to item similarities model) so when I input ITEM_ID the output will be a list of the most similar items. until now things are very smooth but: now I have…
0
votes
1 answer

AWS Personalize — algorithmHyperParameters must be an associative array. Found array

According to documentation (https://docs.aws.amazon.com/aws-sdk-php/v3/api/api-personalize-2018-05-22.html#createsolution), when you create solution, you must provide algorithmHyperParameters as array of strings, so I did: 'solutionConfig' => [ …
Vittore Gravano
  • 706
  • 6
  • 22
0
votes
1 answer

AWS Personalize: Incremental update

To make the Personalize properly function, we need: Users.csv Items.csv Interactions.csv Goal is to import the historical (Interactions) data, and then let it be updated with the real time events. All fine and understandable. How do we go about…
Amiga500
  • 5,874
  • 10
  • 64
  • 117
0
votes
1 answer

AWS Personalize — eventType must be an associative array

Documentation says that eventType must be a string https://docs.aws.amazon.com/aws-sdk-php/v3/api/api-personalize-events-2018-03-22.html#putevents So I did: /* @var PersonalizeEventsClient $client */ $client->putEvents([ 'trackingId' =>…
Vittore Gravano
  • 706
  • 6
  • 22
0
votes
1 answer

"Amazon Personalize" PutItems, PutEvents, PutUsers using aws/aws-sdk-php

I am building an integration between my Laravel application and Amazon Personalize using: aws/aws-sdk-php Everything goes ok, but when I look on how to update the datasets with new Users, interactions and items, I couldn't find the right…
lucianov88
  • 185
  • 3
  • 10