Recommendation types
Below you can find a list of recommendation types you can create in Synerise:
- Cross-sell - This type of recommendation lets you offer complementary items to the ones customers are viewing and at the same time, encourage them to add more items to their shopping carts.
- Similar items - The recommendations of this type are prepared on the basis of information included in the feed.
- Cart recommendations - This type of recommendations allow you to create offers on the basis of the items your customers have added to the cart. The offers are prepared individually for each user, so each of them receive a unique offer adjusted to their preferences.
- Personalized recommendations - This type of recommendation is based on the customers’ purchase preferences and behavioral profile.
- Visual similarity - This type of recommendation that contains items which look similar (regarding shapes, colors, styles, etc.). The recommendations of this type are prepared on the basis of information included in the feed. The module associates items which are alike.
- Last seen - This type of recommendation consists of the items which the customer has already seen.
- Top items - This type of recommendation lets you select items on the basis of a given category to the recommendation offer. A good example of such category is sold items value in the last 30 days. Because the chosen category determines which items will be included in the recommendation offer, then it will be supplemented with a specific number of items which were sold by the highest price during the last 30 days.
- Item comparison - This type of recommendation is an extension of the similar product recommendation - apart from displaying items similar to the context item (currently viewed item), it shows the attributes of similar and viewed items in a table which makes them easy to compare.
- Recent interactions - This type of recommendation allows to promote items towards which the customers performed a specific action which you select. Apart from these most common, such as a visit to the item page, adding the item to the cart, marking the item as favorite, or purchase, you can select any measurable event related to items you sell.
Below, you can find the table that shows how recommendation is generated (the source and context needed):
| Scenario | AI engine | Metric based |
Client context |
Item context |
Multiple items context |
No context |
|---|---|---|---|---|---|---|
| Personalized |  |
|
||||
| Similar items |
|
|
||||
| Visual similarity |
|
|
||||
| Cross-sell | |
|
||||
| Cart recommendations |
|
|
||||
| Last seen | |
|
||||
| Top items | |
|
||||
| Item comparison |
|
|||||
| Recent interactions | |
|
Application of recommendations
The table below presents the application of recommendation types in business scenarios:
| Scenario | Personalized | Similar items |
Visual similarity |
Cross-sell | Cart recommendations |
Last seen | Top items |
Item comparison |
Recent interactions |
|---|---|---|---|---|---|---|---|---|---|
| Home page | |
|
|
|
|||||
| Category/ brand page |
|
|
|
|
|||||
| Product page | |
|
|
|
|
|
|
|
|
| Add to cart | |
|
|
|
|
||||
| Checkout | |
|
|
|
|
||||
| Zero search results |
|
|
|
|
|||||
| Post-purchase | |
|
|
|
|
