> ## Documentation Index
> Fetch the complete documentation index at: https://www.algolia.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Personalized recommendations
> Personalize recommendations for your users.
export const Application = () =>
application
;
export const AlgoliaRecommend = () => ;
This is a **beta feature** according to [Algolia's Terms of Service ("Beta Services")](https://www.algolia.com/policies/terms/).
Personalized recommendations re-rank a model's results using each user's affinities.
Two users who view the same product see the same model, but a different order of recommended items.
Personalized recommendations are compatible with both [Classic](/doc/guides/personalization/classic-personalization/what-is-personalization) and [Advanced](/doc/guides/personalization/advanced-personalization/what-is-advanced-personalization) Personalization.
Personalized recommendations are available for the following models:
* [Frequently bought together](/doc/guides/algolia-recommend/overview#frequently-bought-together)
* [Related items](/doc/guides/algolia-recommend/overview#related-items)
* [Trending items](/doc/guides/algolia-recommend/overview#trending-items-and-trending-facets-value)
* [Looking similar](/doc/guides/algolia-recommend/overview#looking-similar)
## How personalized recommendations work
Personalized recommendations use the same Recommend models, but they incorporate user affinities to tailor the recommendations to individual users.
The recommendations are re-ranked based on users' [affinities](/doc/guides/personalization/classic-personalization/what-is-personalization/in-depth/how-personalization-works#translate-user-behavior-into-affinities-through-events),
which are derived from their interactions and preferences.
Each Recommend request must include the [`userToken`](/doc/api-reference/api-parameters/userToken).
Without it, Recommend doesn't have any affinities to re-rank with and returns the model's default results.
## Before you begin
This feature isn't available on every plan.
Refer to your [pricing plan](https://www.algolia.com/pricing) to see if it's included.
Before you enable personalized recommendations:
* Set up your [Personalization configuration](/doc/guides/personalization/classic-personalization/personalizing-results/in-depth/configuring-personalization) and confirm that user affinities are being computed.
* Check that you [send a `userToken`](/doc/guides/sending-events/concepts/usertoken) with your events, and that each user has their own token.
## Enable personalized recommendations
1. Go to the [Algolia dashboard](https://dashboard.algolia.com/explorer/browse) and select your Algolia .
2. On the left sidebar, select **Recommend**.
3. Select one of the supported models and click **Start using**.
4. On the model's configuration page, turn on **Personalization**.
## Send a user token with your requests
Recommend inherits [`enablePersonalization`](/doc/api-reference/api-parameters/enablePersonalization) from the **Personalization** toggle you turned on for this model in [Enable personalized recommendations](#enable-personalized-recommendations), so you only need to send it to override that setting for a single request.
If you use InstantSearch with the [`insights` middleware](/doc/api-reference/widgets/insights/js), the Recommend widgets send the user token for you.
You can also set `userToken` in the widget's `queryParameters`:
```js JavaScript icon=code theme={"system"}
relatedProducts({
container: "#relatedProducts",
objectIDs: ["OBJECT_ID"],
queryParameters: {
userToken: "user-1234",
enablePersonalization: true, // Optional: overrides the configuration
},
});
```
If you use the [Recommend API client](/doc/libraries/sdk/methods/recommend/get-recommendations), add `userToken` to the `queryParameters` of each request:
```js JavaScript icon=code theme={"system"}
const response = await client.getRecommendations({
requests: [
{
model: "related-products",
indexName: "INDEX_NAME",
objectID: "OBJECT_ID",
threshold: 0,
queryParameters: {
userToken: "user-1234",
enablePersonalization: true, // Optional: overrides the configuration
},
},
],
});
```
Send the same token you send with your click and conversion events.
If you use the Search Insights library, call [`getUserToken`](/doc/guides/sending-events/concepts/usertoken#get-the-user-token-from-search-insights) to get the anonymous user token, instead of generating your own.
## Personalize fallback results
When using a [fallback query](/doc/guides/algolia-recommend/how-to/set-up#show-fallback-recommendations), the results aren't personalized by default.
To personalize fallback results, set `enablePersonalization: true` in `fallbackParameters`:
```js JavaScript icon=code theme={"system"}
relatedProducts({
// ...
fallbackParameters: {
// ...
enablePersonalization: true,
},
});
```
InstantSearch forwards `userToken` into `fallbackParameters` for you.
`enablePersonalization` needs to be set explicitly in `fallbackParameters`.
If you use the Recommend API client or an older version of InstantSearch, set both `userToken` and `enablePersonalization` in `fallbackParameters`.
## See also
* [Recommended for you](/doc/guides/algolia-recommend/how-to/recommended-for-you), a model that's personalized by design
* [Set up Recommend](/doc/guides/algolia-recommend/how-to/set-up)
## Send a user token with your requests
Recommend inherits [`enablePersonalization`](/doc/api-reference/api-parameters/enablePersonalization) from the **Personalization** toggle you turned on for this model in [Enable personalized recommendations](#enable-personalized-recommendations), so you only need to send it to override that setting for a single request.
If you use InstantSearch with the [`insights` middleware](/doc/api-reference/widgets/insights/js), the Recommend widgets send the user token for you.
You can also set `userToken` in the widget's `queryParameters`:
```js JavaScript icon=code theme={"system"}
relatedProducts({
container: "#relatedProducts",
objectIDs: ["OBJECT_ID"],
queryParameters: {
userToken: "user-1234",
enablePersonalization: true, // Optional: overrides the configuration
},
});
```
If you use the [Recommend API client](/doc/libraries/sdk/methods/recommend/get-recommendations), add `userToken` to the `queryParameters` of each request:
```js JavaScript icon=code theme={"system"}
const response = await client.getRecommendations({
requests: [
{
model: "related-products",
indexName: "INDEX_NAME",
objectID: "OBJECT_ID",
threshold: 0,
queryParameters: {
userToken: "user-1234",
enablePersonalization: true, // Optional: overrides the configuration
},
},
],
});
```
Send the same token you send with your click and conversion events.
If you use the Search Insights library, call [`getUserToken`](/doc/guides/sending-events/concepts/usertoken#get-the-user-token-from-search-insights) to get the anonymous user token, instead of generating your own.
## Personalize fallback results
When using a [fallback query](/doc/guides/algolia-recommend/how-to/set-up#show-fallback-recommendations), the results aren't personalized by default.
To personalize fallback results, set `enablePersonalization: true` in `fallbackParameters`:
```js JavaScript icon=code theme={"system"}
relatedProducts({
// ...
fallbackParameters: {
// ...
enablePersonalization: true,
},
});
```
InstantSearch forwards `userToken` into `fallbackParameters` for you.
`enablePersonalization` needs to be set explicitly in `fallbackParameters`.
If you use the Recommend API client or an older version of InstantSearch, set both `userToken` and `enablePersonalization` in `fallbackParameters`.
## See also
* [Recommended for you](/doc/guides/algolia-recommend/how-to/recommended-for-you), a model that's personalized by design
* [Set up Recommend](/doc/guides/algolia-recommend/how-to/set-up)