Skip to main content
Personalization strengthens interactive search. It adds a personal layer to your relevance strategy. It uses each user’s preferences to make the search experience more relevant to them.
This feature isn’t available on every plan. Refer to your pricing plan to see if it’s included.

​
Advantages of personalization

Algolia’s out-of-the-box relevance strategy treats every user the same way. Personalization considers a user’s specific tastes instead. Textual relevance and custom ranking establish the baseline ranking. Personalization then adjusts that ranking based on each user’s preferences. Queries mean different things to different people. For example, take a user who searches for “harry” and likes children’s books. They might prefer to see “Harry Potter” results on the first page. Some users follow politics instead. They may be more interested in seeing “Harry Truman” in their results. Personalization uses a user’s past behavior to find the most relevant results. Better relevance minimizes the user’s effort to find what they want. They see more options they’re likely to find appealing. Algolia’s Personalization feature brings this capability to your business.

​
How does Personalization fit into Algolia’s relevance strategy?

Effective relevance has two main goals:
  • Enabling your users to find results that match their expectations.
  • Providing results that align with your business needs.
You can address these twin goals by tuning the first three layers of Algolia’s relevance strategy:
  1. Textual relevance. Matching that includes typo tolerance, synonyms, natural language processing, and other settings.
  2. Custom ranking. Ranking results using attributes and metrics that matter for your search experience.
  3. Merchandising. Boosting and burying specific results or categories using Rules.
You can also enable Dynamic Re-ranking. It boosts trending results and categories using search data from all your users. All these contribute, in different ways, to relevant results. These results apply equally to all your users. Personalization works alongside these to customize search results for each user. It doesn’t replace Algolia’s ranking algorithm. Instead, it refines the results by changing their order. This promotes the results that best match each user’s affinities. This can increase user engagement. It can also drive more conversions. Algolia applies Personalization after it computes your results’ textual relevance. It then applies your custom ranking. If you use Rules, the engine applies them after the Personalization. You may have enabled both Personalization and Dynamic Re-Ranking. If so, the engine doesn’t apply them at the same time. Instead, it applies:
  • Personalization for users with enough data to personalize the search
  • Re-ranking for users without enough data to personalize the search (such as first-time users).

​
The order of relevance strategies

In summary, the engine applies the relevance strategies in this order:
  1. Textual relevance (through the textual ranking criteria)
  2. Business relevance (through custom ranking)
  3. User-based preferences (through either Personalization or Dynamic Re-Ranking)
  4. Merchandising (through Rules)
There’s one exception. It’s when you’ve set your Personalization impact to 100. In that case, the engine prioritizes Personalization over business relevance. Then the engine applies the relevance strategies in this order:
  1. Textual relevance (through the textual ranking criteria)
  2. User-based preferences (through Personalization)
  3. Business relevance (through custom ranking)
  4. User-based preferences (through Dynamic Re-ranking, only if there isn’t enough data to personalize results for a particular user)
  5. Merchandising (through Rules)
Before you enable Personalization, simulate your personalization strategy first. Then, A/B test the effects of Personalization.

​
See also

Last modified on September 16, 2026