---
title: About Session-Based Product Recommendations (SBPR)
slug: m5rd0471
canonical_url: https://docs.coveo.com/en/m5rd0471/
collection: coveo-for-commerce
source_format: adoc
---
# About Session-Based Product Recommendations (SBPR)
[Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [Session-Based Product Recommendation (SBPR)](https://docs.coveo.com/en/m7db5404/) [models](https://docs.coveo.com/en/1012/) take advantage of [Coveo Personalization-as-you-go](https://docs.coveo.com/en/m5kd0347/) capabilities to suggest relevant products based on current user interactions with a Coveo-powered commerce implementation.

Unlike traditional [product recommendation](https://docs.coveo.com/en/3132/) models, which suggest products based on co-occurrence patterns using machine learning methods that rely on the frequency of past interactions, SBPR models leverage [product embeddings](https://docs.coveo.com/en/laei9434/) and [user session vectors](https://docs.coveo.com/en/nbla0227/) to determine which products to recommend.

SBPR models leverage [user session vectors](https://docs.coveo.com/en/nab90474/) to update the recommendations provided in real time.
The algorithm continuously processes the actions taken by the user to recommend products that are relevant to their current shopping session.
This is also useful in scenarios where users aren't authenticated, as the algorithm can infer the user's intentions as soon as they start interacting with the interface.

**Example**

During a shopping session on a Coveo-powered sporting goods commerce interface, an unauthenticated user performs the following actions:

. Enters `Golf iron sets` in the search box.

. Navigates through the iron sets that are being displayed on the results page, and then clicks on mid-range golf iron sets.

. Enters `Golf driver` in the search box, navigates through the available drivers, and then returns to the home page.

By analyzing the user's session, the model understands that they're currently looking for mid-range golf equipment.
Therefore, since the recommendations interface on the home page leverages an SBPR model, the products displayed to the current user are complementary products, such as mid-range golf gloves and balls.

## Prerequisites

> **Important**
>
> Contact your Coveo representative to enable SBPR in your [Coveo organization](https://docs.coveo.com/en/185/).

To use SBPR, you must meet the following prerequisites:

* Your organization must contain at least one [Catalog source](https://docs.coveo.com/en/n8of0593/).

> **Note**
>
> The [field](https://docs.coveo.com/en/200/) that uniquely identifies the [items](https://docs.coveo.com/en/pa8f6515/) in the Catalog source, such as `ec_product_id`, must be [mapped to the `permanentid` field](https://docs.coveo.com/en/n8of7021#map-to-permanentid).
> 
> To train [Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [models](https://docs.coveo.com/en/1012/), you can't use the `#` character in either of these fields.
> See [Manage source mappings](https://docs.coveo.com/en/1640/) for instructions on how to define mappings on a source.

* Your commerce interface must track, at a minimum, the following [commerce events](https://docs.coveo.com/en/o1n91230#capture-events):

** [Click events](https://docs.coveo.com/en/o1n92447/)

** [Product view events](https://docs.coveo.com/en/o1n93101/)

** [Cart events](https://docs.coveo.com/en/o1n93466/)

** [Purchase events](https://docs.coveo.com/en/o1n93059/)