Every other recommendation widget answers “which item should this visitor see”. These answer a different question: which part of the site should they go to next — a product category, an article topic, or an article category.
Watch the 1:36 walkthrough: picking a template, choosing the page, and dropping a shop-by-category block into a slot you already have.
It is a small difference with a large consequence. A visitor who does not yet know what they want cannot be sold a specific jacket; they can be shown that Outerwear is where their kind of visitor ends up.
The three actions
| Action | Recommends | Draws on | Add it in |
|---|---|---|---|
| Category Recommender for Products | Product categories | The product catalog and product behaviour — views, carts, purchases | A Product Recommendations campaign |
| Interest Recommender for Content | Article topics — your interests | The content catalog and reading behaviour — reads, goals reached, comments, likes | A Content Recommendations campaign |
| Category Recommender for Content | The categories your articles are filed under | The same reading behaviour, one level up from articles | A Content Recommendations campaign |
Adding one: New campaign → Product Recommendations (or Content Recommendations) → the Content step → Add action → Category recommendations (then Products for product categories, or Content for your content sections), or Interest recommendations for topics. Each is built in the same three steps as any other recommendation: Select Recommendation Algorithm, Customize Look & Feel, Placement, Trigger & Frequency.
When to reach for one
- The homepage of a first-time visitor. There is no browsing history to recommend products from, but there is always a most-popular category — and it is a better first question than a carousel of arbitrary items.
- After a purchase. The thank-you page is the wrong place for another of the thing they just bought, and the right place for the aisle next door.
- A dead end — an empty search, an error page, an out-of-stock product. A category is something to offer when there is no item to offer.
- Publishing. On a content site, “more like this” at the topic level often beats another single article, because it commits the reader to a direction rather than one more page. A reader who does not yet know which article they want can still be shown the topic their kind of reader goes to next.
A new one starts on the most viewed (or most read) categories lately, the same for every visitor; the personal algorithms below are a choice in the algorithm step.
What it can show
Each recommended category or topic can carry its name, an image, and a count of what is inside it — “6 items”, “3 articles”. The count is worth showing: it is the difference between a label and a promise of something behind it.
The designs
The same recommendation, three ways. Which one you pick is a layout decision, not an algorithm one — every design works with every algorithm below.
| Design | Looks like | Best for |
|---|---|---|
| Category Tiles (Topic Tiles for interests) | A photo grid with the name set on the picture. | A homepage section in its own right — the most prominent. |
| Category Strip (Topic Strip) | Round pictures in a scrolling row — the pattern shoppers know from category navigation. | Sitting quietly under a header. |
| Category List (Topic List) | Names and counts, no images. | Sidebars, narrow columns, and categories with no artwork worth showing. |
Category Recommender for Products also offers two text-only designs: Text Links, No Thumbnails and Title on the Left, Categories Beside It.
Recommend interests uses the same three, in the content vocabulary:
The algorithms
Each of the three has thirteen, and they pair across the actions — the same engine, named for what it reads. Pick the row, then the column for the action you are building. The picker offers three pages: General (the whole visit), Category, and the Product Page or Article Page, and groups the algorithms as Personalized & Popular, Co-Views & Related and Visitor History & Popularity.
| Product categories | Article topics (interests) | Article categories | What it picks | Pages |
|---|---|---|---|---|
| Personalized Recommendations | Personalized Recommendations | Personalized Recommendations | What visitors with similar demographics engage with. The best homepage default. | All three |
| Most Popular Category | Most Popular Interest | Most Popular Category | Site-wide, by views or reads, over the period you choose. | General, Category |
| Most Bought Category | Most Converting Interest | Most Converting Category | Site-wide, by purchases — or by goals reached. | General, Category |
| Trending Categories | Trending Interests | Trending Categories | Whatever is getting far more activity today than its own weekly average. Trending by picks the signal. | General, Category |
| Others Who Viewed Also Viewed | Others Who Read Also Read | Others Who Read Also Read | A co-view collaborative filter, one level up from items. On a Category page, anchored to the category being viewed. | All three |
| What others Bought, who Viewed this | What Converting Readers Were Interested In | What Converting Readers Read | A view→buy, or read→goal, collaborative filter. | All three |
| You May Like | You May Like | You May Like | Personalized, but anchored to the product or article on the page. | Item page |
| Currently Viewing | Currently Reading | Currently Reading | The category or topic of the item on this page, when the page reports one. | Item page |
| Categories in the Cart or Wishlist | Interests Commented On or Liked | Categories Commented On or Liked | Read from the live session: what is in the cart or wishlist right now, or what the reader commented on or liked. On-site only. | All three |
| Recently or Most Viewed Category | Recently or Most Read Interest | Recently or Most Read Category | This visitor’s own history: where they have actually been. Order: most recent, oldest, most often, or strongest. | General, Category |
| Category of Recently Viewed Product | Interest of Recently Read Article | Category of Recently Read Article | Inferred upward from the individual items they looked at. | General, Category |
| Past Orders Recommendations | Past Goals Recommendations | Past Goals Recommendations | Related to what this visitor bought, or the goals they reached. | Item page |
| Buy it Again | Reached Goal Again | Reached Goal Again | Categories they bought from, or topics they converted on, before. | Item page |
What it needs before it can return anything
- For product categories: a product catalog whose items carry categories, and category tracking on your pages so the engine knows which category a visitor is in — Settings → Recommendation setup → Product Tracking → Categories. See product interaction tracking.
- For topics: interests set on your articles — from the feed, from the contextual engine, or by hand.
- For article categories: a content catalog whose articles carry categories, and article tracking.
- Reading or browsing history for the personal algorithms. For a first-time visitor, a popular or trending category is the better first question.
- A page address for each category or topic. Each one shows as a link to its page, so only the ones that have a page address can be shown. Add action and the algorithm step say how many of yours have one — “12 of your 30 categories have a page address – only those can be shown.” — or that none has, “so this would show nothing”. The addresses come in by import: no panel screen sets them, and the product and content feeds carry a category’s name only.
- An image per category, if you want the tiles or strip design. The list design needs none.
Related
- Recommendation algorithms — the item-level engines, and how the page anchor works.
- Product interaction tracking — including categories and interests.
- Interests for recommendations
- Setting the product / content feed
- Content recommendations — recommending single articles.