> For the complete documentation index, see [llms.txt](https://rosetta-ai.gitbook.io/help-center/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://rosetta-ai.gitbook.io/help-center/functions/recommenders/recommendation-type.md). # Introduction to Recommendation Types Rosetta.ai has designed **eight different recommendation types** tailored to various products and scenarios. Store owners can choose different recommendation types based on their product categories or pages. Below is an introduction to the recommendation types: ## 1. You’ll Love Me {% hint style="info" %} Recommended Placement: All Pages {% endhint %} {% hint style="success" %} This feature is available for users with the **Professional** plan and above. {% endhint %} Rosetta AI's core recommendation uses AI deep learning technology to analyze the entire site's consumer behavior and preferences within 24 hours. It predicts in real-time the products that incoming visitors are most likely to purchase and enjoy. As visitors interact with products more frequently, the recommendation system becomes more precise, creating personalized recommendations. This type of recommendation offers a comprehensive range of related products, enhancing customer retention and brand loyalty. ## 2. Steadily Popular {% hint style="info" %} Recommended Placement: Homepage, Product List Pages {% endhint %} Based on statistical data from all site users, this recommendation considers the cumulative multi-indicator behaviors (such as browsing, clicking, purchasing, etc.) on a **monthly** basis. It offers comprehensive recommendations, not solely based on sales volume, ensuring that visitors see products that interest a significant portion of others, resulting in higher click-through rates. ## 3. Trending Now {% hint style="info" %} Recommended Placement: Product List Pages {% endhint %} This recommendation analyzes the cumulative multi-indicator behaviors' growth rates (such as browsing, clicking, purchasing, etc.) within the **past two weeks** to identify current trends. Unlike most recommendation systems that prioritize sales volume, Rosetta AI's recommendation system provides a more comprehensive view, giving less popular products a chance to be recommended. ## 4. Suddenly Hot {% hint style="info" %} Recommended Placement: Product List Pages during short-term promotions {% endhint %} This recommendation suggests products based on the growth rates of multi-indicator behaviors over a **short period**, providing immediate exposure to new products. ## 5. Similar Products {% hint style="info" %} Recommended Placement: Product Detail Pages {% endhint %} This recommendation suggests related products based on the **similarity of product descriptions or names**, automatically displaying the most closely related items. It encourages consumers to explore other recommended products instead of leaving the current product page or exiting the website. ## 6. Like What You Bought Before {% hint style="info" %} Recommended Placement: Product Detail Pages, Shopping Cart {% endhint %} This recommendation is based on a consumer's browsing behavior since entering the site. It aims to capture returning customers who often browse various products but ultimately purchase unrelated items. It automatically suggests products related to the one the customer is currently viewing or **products with the highest likelihood of purchase** but from different categories, leveraging their past purchase history on your website. ## 7. Frequently Bought Together {% hint style="info" %} Recommended Placement: Shopping Cart {% endhint %} This recommendation analyzes the multi-indicator behaviors (including clicks, browsing, and purchases) of products within the shopping cart. It automatically suggests combinations of products that are frequently purchased or browsed together, facilitating **cross-selling**. For example, suggesting sock-shoe combinations to increase the number of items in the cart and the average order value. ## 8. Realtime Preference {% hint style="info" %} Recommended Placement: Product Details Page {% endhint %} {% hint style="success" %} This feature is available for users with the **Professional** plan and above. {% endhint %} Provide real-time prediction on customers’ potential favorite and interesting products and update recommended products to them based on their behavior (including clicks and browsing). For example: when consumer A enters the site and has clicked on black short-sleeved tops and black bags, the recommendation section will instantly recommend black dresses and related tops to the consumer. In the next chapter, we’ll explain how to [select a layout style](/help-center/functions/recommenders/layout-style.md) for your recommendation. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://rosetta-ai.gitbook.io/help-center/functions/recommenders/recommendation-type.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.