Under the hood recommendations rely on supervised machine learning models and the Algolia foundation.

For both models, the data corresponding to the past 30 days is collected. This results in a matrix where columns are userTokens and rows are objectIDs. Each cell represents the number of interactions (click and/or conversions) between a userToken and an objectID. Then, Algolia Recommend applies a collaborative filtering algorithm: for each item, it finds other items that share similar buying patterns across customers. Items would be considered similar if the same users set interacted with them. Items would be considered bought together if the same set of users bought them.

Algolia’s AI Recommendations serves a wide range of industries like B2C and B2B ecommerce, marketplaces, media, SaaS, fashion, and more. 

Each industry can leverage the recommendation engine's flexibility to create tailored experiences that match their specific user needs and business objectives.

Very fast. Most recommendation requests will take from 1 to 20 milliseconds to process. This lightning-fast response time gives users instant suggestions without any noticeable delay.

Implementing AI Recommendations is straightforward, four-step process:

• Capture your users' conversion events - Track user interactions like clicks, views, and purchases

• Send your data to Algolia - Upload your behavioral data to the platform

• Train the models with the push of a button - Let Algolia's AI process and learn from your data

• Add recommendations to your UI - Integrate the recommendation widgets into your website or app

Learn more about getting started with AI Recommendations 

Yes, Algolia's recommendation engine is completely language-agnostic. It supports alphabet-based and symbol-based languages such as Chinese, Japanese, and Korean, making it suitable for global businesses operating in diverse markets.

AI recommendation engines analyze the full sequence and context of a user’s behavior. Traditional recommendation engines, on the other hand, often base their suggestions on only a single action like the most recent item viewed or purchased. 

By leveraging AI, recommendation engines can detect patterns, predict intent, and deliver more relevant, personalized recommendations that adapt in real time as the user interacts with your site or app.