---
title: About the cold start feature
slug: na2a8306
canonical_url: https://docs.coveo.com/en/na2a8306/
collection: coveo-for-commerce
source_format: adoc
---
# About the cold start feature
[Coveo Personalization-as-you-go](https://docs.coveo.com/en/m5kd0347/) (PAYG) models rely on [product vectors](https://docs.coveo.com/en/nbla0256/) and [embeddings](https://docs.coveo.com/en/ncc87383/), as well as on [user session vectors](https://docs.coveo.com/en/nbla0227/) to deliver personalized recommendations and search results for each customer.
These models are built by identifying relationships between [indexed](https://docs.coveo.com/en/204/) products based on behavioral data.

PAYG models ([IAPR](https://docs.coveo.com/en/m61h0552/) and [PQS](https://docs.coveo.com/en/m1ol5526/)) can generate meaningful representations of user behavior in the form of vectors, which are then embedded directly into the [catalog entity](https://docs.coveo.com/en/3143/).
However, when dealing with long tail (less popular) or new products, traditional algorithms may not have a sufficiently large sample size to establish precise vector representations.

To optimize your product inventory coverage and enhance the accuracy of recommendations and search results, the [index](https://docs.coveo.com/en/204/)’s [embedding](https://docs.coveo.com/en/ncc87383/) procedure integrates a cold start feature.
This allows for precise positioning of products within the vector space, even when they have limited or no traffic data associated with them.

## How does the cold start feature work?

![Representative example of the Cold Start feature | Coveo](https://docs.coveo.com/en/assets/images/coveo-for-commerce/images/cold-start-visual.png)

The cold start feature effectively positions products in the vector space, regardless of the traffic volumes they receive.
To achieve this, instead of depending solely on customer interactions with a product, the cold start feature uses the product's attributes to generate a [product vector](https://docs.coveo.com/en/nbla0256/) and position it within the vector space.

By adding product attributes to the model, such as the category, brand, and description, the [embedding](https://docs.coveo.com/en/ncc87383/) procedure is able to capture the essence of a product and reliably generate a [product vector](https://docs.coveo.com/en/nbla0256/), even for new products that have no interactions yet.
This means that low interaction products, or new products, can be suggested by [Coveo ML](https://docs.coveo.com/en/188/) PAYG models as soon as they're added to the [index](https://docs.coveo.com/en/204/).