Recommendation AI

[PMLE-EXAMTOPIC] Reccomendation AI - Obtimization objectives based on Recommendation types

This post is about the specific examtopic on Google Professional Machine Learning Engineer Certificate.

Recommendation AI

Steps to implement recommendation AI

• Import product catalog
• Record user event
• Determine recommendation Type & Placements

Optimization Objs & Customization ways based on Recommendation types

• Others You May Like : click-through rate CTR
  • Change optimization objective to conversion rate
  • Add price reranking
  • Add diversification (supported but not recommended)
• Frequently Bought Together : revenue per order
  • Add diversification
• Recommended for You : click-through rate CTR
  • Change optimization objective to conversion rate
  • Add price reranking
  • Add diversification
• Recently Viewed : not recommendation but user history

Optimization objectives

* Click-through rate (CTR)

Optimizing for CTR emphasizes engagement to maximize the likelihood that the user interacts with the recommendation.

* Revenue per order

The revenue per order optimization objective is the default optimization objective for the "Frequently Bought Together" recommendation model type

* Conversion rate (CVR)

Optimizing for conversion rate maximizes the likelihood that the user adds the recommended item to their cart

Advance options

• Diversification : If you want to ensure that results returned from a single prediction request are from different categories of your product catalog, you can enable diversification.Diversification reduces the likelihood that similar catalog items are shown in the recommendation panel, at the risk of removing some good recommendations.
• Price reranking: Price reranking causes recommended catalog items with a similar recommendation probability to be ordered by price, with the highest- priced items first.
• Results filtering : You can filter the prediction results for a placement by the tag value you provided with the catalog item and by whether the item is in stock
• Available placements: review statistics about where recommendations appear.