Recommendations - bobbae/gcp GitHub Wiki
Recommendations AI enables you to build an end to end personalized recommendation system based on state-of-the-art deep learning ML models, without a need for expertise in ML or recommendation systems.
Overview
You can use Recommendations AI to get personalized recommendations for your website whether or not you are using Google marketing tools. However, if you are using Google Tag Manager or Google Merchant Center, some steps to implement Recommendations AI are simplified.
Implementing Recommendations AI with Google marketing
https://cloud.google.com/retail/recommendations-ai/docs/overview#quick-implementation
Concepts
https://cloud.google.com/retail/recommendations-ai/docs/concepts
Features
https://cloud.google.com/retail/recommendations-ai/docs/features
Catalogs
The catalog data you import into Recommendations AI has a direct effect on the quality of the resulting model, and therefore on the quality of the predictions Recommendations AI provides. In general, the more accurate and specific catalog information you can provide, the higher quality your model.
Your catalog should be kept up to date. You can upload catalog changes as often as needed; ideally, every day for catalogs with a high rate of change. You can upload (patch) existing product items; only the changed fields will be updated. There is no charge for uploading catalog information.
Recommendation Model Types
When you sign up to use Recommendations AI, you work with Recommendations AI Support to determine the best recommendation models and customizations to use for your site. The models and customizations you use depend on your business needs, and where you plan to display the resulting recommendations.
When you request recommendations from Recommendations AI, you provide the placement value, which determines which model is used to return your recommendations.
User Events
https://cloud.google.com/retail/recommendations-ai/docs/user-events
Attribution Tokens
https://cloud.google.com/retail/recommendations-ai/docs/attribution-tokens
A/B Testing
An A/B experiment is a randomized experiment with two groups: an experimental group and a control group. The experimental group receives some different treatment (in this case, predictions from Recommendations AI); the control group does not.
When you run an A/B experiment with Recommendations AI, you include the information about which group a user was in when you record user events. Recommendations AI uses that information to refine the model and provide metrics.
Both versions of your application must be the same, except that users in the experimental group see recommendations generated by Recommendations AI and the control group does not. You log user events for both groups.
Audit
https://cloud.google.com/retail/recommendations-ai/docs/audit-logging
How-to
https://cloud.google.com/retail/recommendations-ai/docs/how-to
Alerts
Keeping your catalog up to date and recording user events successfully is important for getting high-quality recommendations. Even if your initial imports and event recording are successful, monitoring error rates is still needed in case of unexpected environmental issues, such as network connectivity failures.
APIs
https://cloud.google.com/retail/recommendations-ai/docs/apis
ML-fueled recommendations and Active assist
Videos
https://cloud.google.com/retail/recommendations-ai/docs#videos
Building Recommendation systems with Deep learning instead of matrix multiplication
https://medium.com/google-cloud/recommendation-systems-with-deep-learning-69e5c1772571
Tutorials
Creating Personalized Movie recommendations
https://cloud.google.com/retail/recommendations-ai/docs/movie-rec-tutorial
IKEA Case study
https://cloud.google.com/blog/products/ai-machine-learning/ikea-uses-google-cloud-recommendations-ai
Retail recommendations
Data Ingestion from different sources
https://cloud.google.com/blog/topics/developers-practitioners/recommendations-ai-data-ingestion