This article is relevant only to the Restaurants vertical
The following table lists all the Experience OS Restaurant algorithms.
| Algorithm | Description | Fallback |
|---|---|---|
| Popular in Store | Drives engagement by suggesting the most popular items purchased by customers at a specific store location. | No fallback |
| User Favorites | Drives personalization recommendations by suggesting items the user has purchased most frequently and recently. | Popular in store |
| User Picks | Drives personalized recommendations by suggesting items the user is most likely to purchase, based on their purchase history, using machine learning models. | User Favorites › Popular in store |
| Purchased Together | Increases take rate by suggesting items most frequently purchased together with the last selected item. | Popular in store |
| Adaptive Purchased Together | Increases take rate by suggesting items frequently purchased together, continuously adapting through a feedback loop based on user behavior. | Purchased Together › Popular in store |
| Purchased Together with Items in Cart | Increases take rate by suggesting items frequently purchased with the products currently in the cart, using deep learning models. | Purchased Together › Popular in store |
| Purchased Together with Frequently Purchased | Increases take rate by suggesting items frequently purchased by others, while also considering the user’s most frequently purchased items. | User Favorites › Popular in store |
| Add-ons | Increases basket size by suggesting complementary items based on the user’s current selections. | Popular in store |
| User Picks with Items in Cart | Drives personalized recommendations by suggesting items the user is likely to purchase, based on both their purchase history and the items currently in the cart, using machine learning models. | User Favorites › Popular in store |
| AOV Boost | Increases Average Order Value (AOV) by suggesting products proven to drive larger orders, based on real-time data and overall purchase trends. | Popular in store |
| AOV Boost Sets | Increases AOV by suggesting product sets proven to drive larger orders, based on real-time data and overall purchase trends. | Popular in store |
| User Picks with AOV Boost | Increases AOV by suggesting products proven to drive larger orders, while also considering the user’s personal purchase history. | User Favorites › Popular in store |
| Multi-Context Picks | Drives engagement and AOV by using AI-powered contextual models to suggest items based on Time of Day, Type of Day, Weather, and Area Type/Audience Type. Available only for Pre-Order and Before-Paying widget types. | Popular in store |