About Intent-Aware Product Ranking (IAPR)

This is for:

Developer

Coveo Machine Learning (Coveo ML) Intent-Aware Product Ranking (IAPR) models rank products on search result pages based on a customer’s shopping intent.

IAPR models leverage Coveo’s product embeddings and vectors capabilities. Leveraging these capabilities allows IAPR models to detect customers' shopping objectives and react to intent changes in real time. This means that IAPR models react to customers' queries by boosting products that match the current customer’s shopping context, whether they’re authenticated or not.

illustration of IAPR outputs | Coveo

Members with the required privileges can configure and activate Coveo ML IAPR models using the Coveo Administration Console. See Manage Intent-Aware Product Ranking models for instructions.

How do IAPR models work?

IAPR models leverage advanced deep learning techniques to deliver contextually relevant search results to your customers. To achieve this, they rely on the interactions between product and user session vectors.

Product vectors are representations of the products available in your catalog, where similar products are close to each other. These vectors capture relationships between products based on user behavior and customer data.

User session vectors are generated based on customer interactions and events within their current browsing session. Product detail view events, which indicate customer engagement with specific products during the session, are essential in shaping this vector. They’re vital for understanding the customer’s immediate interests and preferences.

A user session vector evolves dynamically as the customer interacts with your website during their session. It reflects the customer’s behavior, interests, and interactions in real time, making it a crucial element in returning contextually relevant search results.

How do IAPR models leverage product and user session vectors?

IAPR continuously analyzes the customer browsing session to detect their shopping intent. By understanding what products or categories the customer is actively exploring and their level of interest in specific attributes or features, IAPR adapts product rankings in real time. It ensures that products are ranked not solely based on their general popularity but also by their contextual relevance to the customer’s current session. This means products that align with the customer’s session context receive higher rankings.

IAPR models leverage product and user session vectors to determine the customer’s intent and rank products accordingly. Here’s a detailed look at how IAPR leverages these capabilities:

  • By continuously analyzing the detail view events of a customer’s session, the model detects their shopping intent and generates a user session vector.

  • IAPR relies on product vectors to uncover relationships between products in your catalog. These relationships are learned from customer interactions, revealing which products are frequently associated with, or complement each other.

  • IAPR combines the customer’s session context, as represented by the session vector, with the product relationships encoded in product vectors. By identifying the products that share the most similarities with the customer’s current session, IAPR can rank products that are most likely to align with the customer’s intent.

About the Cold Start feature

Product vectors are generated based on customer interactions with the different products in your catalog. This means that the more interactions a product has, the more accurate its vector representation will be.

But what if a product has none or very few interactions? IAPR models integrate a Cold Start feature to address this issue. This feature allows IAPR models to leverage the product’s metadata to build its vector representation and place it accurately within the vector space. For more information, see About the Cold Start feature.