Anchor product
Jenny High-Back Dining Chair, Set of 2
$349.00
- Dining chair
- Rolled back
- Dark tapered legs
- Slate grey
How it works
Real-time user behavior collection powers personalized experiences.
Fulcrum captures every single interaction from every single user every single time. Continuous data collection on what each individual user does powers highly personalized experiences, increasing engagement and accelerating conversion.
Fulcrum employs custom algorithms targeted to specific users that are proven formulas to generate increased conversion and incremental revenue.
Coverage
Individual algorithms for specific user segments.
Fulcrum automatically identifies a user based on their segment and generates personalized experiences and product recommendations that match the user's behavior, as well as their stage within the funnel/customer journey.
-
Similar Products
Item-to-item matching on type, brand, price band and material.
See an example → -
Frequently Bought Together
Products that actually co-occur in your order history.
See an example → -
Customers Also Bought
Affinity across sessions, surfacing adjacent categories.
See an example → -
Viewed Together
Products visitors compare in the same session.
See an example → -
Recently Viewed
The visitor's own browsing history, brought back into view.
-
Top Sellers
Real-time product velocity, matched against inventory.
-
Abandon Cart Triggers
Exit intent triggers an on-site recovery moment.
-
Replenishment
A predicted reorder interval per customer, timed to when they run out.
Selection
One viewed product, three different visitors.
Four algorithms above are each shown against one viewed product for three visitors Fulcrum knows different things about. The viewed product stays the same. The recommendations change with the visitor, and each one states why it earned its slot.
Products, prices and visitor personas are examples, not client data. Product images are from Amazon Berkeley Objects and licensed under CC BY 4.0.
Visual similarity
Similar chairs ranked by visual match
This algorithm compares product images by shape, proportions, legs, upholstery and colour. It does not need order history, so it can recommend new products immediately. It excludes chairs the visitor has already saved or bought.
Visitor A
First-time visitor
Fulcrum saw
First pageview, no history
BASELINE
1
Jenny High-Back Dining Chair, Set of 2
Why: Same design and dimensions in navy.
2
Reinhart Upholstered Dining Chair, Set of 2
Why: Rolled back, dark tapered legs and similar price.
3
Lamberton Nailhead Dining Chair, Set of 2
Why: Similar curved back, nailhead trim and oak legs.
4
Lamberton Curved-Back Chair, Set of 2
Why: Similar silhouette in a lighter neutral colour.
Visitor B
Saved the navy chair last week
Fulcrum saw
Wishlist add - Jenny High-Back, navy
1
Reinhart Upholstered Dining Chair, Set of 2
Why: Closest match after removing navy Jenny.
2
Lamberton Nailhead Dining Chair, Set of 2
Why: Similar curved back, nailhead trim and oak legs.
3
Lamberton Curved-Back Chair, Set of 2
Why: Similar silhouette in a lighter neutral colour.
4
Hughes Casual Wood Kitchen Chair, Set of 2
Why: Similar wood legs at a lower price.
Change: The navy Jenny drops out because it is already saved. Hughes takes the fourth position as the next closest visual match.
Visitor C
Bought the grey Lamberton set in March
Fulcrum saw
Order history - Lamberton Nailhead, grey
1
Jenny High-Back Dining Chair, Set of 2
Why: Same design and dimensions in navy.
2
Reinhart Upholstered Dining Chair, Set of 2
Why: Rolled back, dark tapered legs, similar price.
3
Classic Wishbone Dining Chair, Set of 2
Why: Different silhouette for a second room.
4
Hughes Casual Wood Kitchen Chair, Set of 2
Why: Similar wood legs at a lower price.
Change: Both Lamberton chairs drop out. The visitor owns the grey frame, and the beige chair is the same design in another colour. Wishbone and Hughes fill the slots.
Products rank first by visual similarity, then by price. The algorithm works without order history, including for new and low-volume products. When history exists, it removes products the visitor has saved or bought.
Frequently bought together
Products frequently bought with this coffee maker
This algorithm uses order history to find products commonly purchased with the coffee maker. It recommends complementary products rather than alternatives and skips anything the visitor has already bought or has in the cart.
Anchor product
12-Cup Digital Coffee Maker
$54.99
- Drip coffee maker
- 12 cup carafe
- Reusable filter
- Whole bean or ground
Visitor A
First-time visitor
Fulcrum saw
First pageview, no history
BASELINE
1
Nicaragua Whole Bean Coffee, 12 oz
Why: Most often bought with this coffee maker.
2
Electric Coffee Bean Grinder
Why: Often bought with the maker and whole beans.
3
Portia Glass Coffee Mugs, Set of 2
Why: Most common drinkware purchase with this maker.
4
Electric Milk Frother and Heater
Why: Bought with this maker less often.
Visitor B
Ordered the grinder last month
Fulcrum saw
Order history - Electric Coffee Bean Grinder
1
Nicaragua Whole Bean Coffee, 12 oz
Why: Most often bought with this coffee maker.
2
Portia Glass Coffee Mugs, Set of 2
Why: Most common drinkware purchase with this maker.
3
Electric Milk Frother and Heater
Why: Bought with this maker less often.
4
Stainless Steel Tumbler
Why: Bought with this maker by grinder owners.
Change: The grinder drops out because it shipped last month. The tumbler takes its place because grinder owners buy it with this maker more often than anyone else.
Visitor C
Whole bean coffee already in the cart
Fulcrum saw
Cart - Nicaragua Whole Bean Coffee, 12 oz
1
Electric Coffee Bean Grinder
Why: First: beans are in the basket, but no grinder.
2
Portia Glass Coffee Mugs, Set of 2
Why: Most common drinkware purchase with this maker.
3
Hazelnut Coffee Creamer, 32 fl oz
Why: Most common consumable added alongside beans.
4
Electric Milk Frother and Heater
Why: Bought with this maker less often.
Change: The beans drop out because they are already in the cart. The creamer takes their place because it is the consumable most often added alongside beans in the same basket.
Ranking reflects how often products are bought with this maker compared with alone. Recommendations update as order patterns change. Products already owned or in the basket are removed before ranking.
Customers also bought
Products tote buyers often buy next
This algorithm looks across customer purchase history, not just one order. It finds products bought by the same customers in later purchases, then removes what this visitor has already bought or is carrying.
Anchor product
Structured Shoulder Tote
$47.99
- Tote bag
- Faux leather
- Beige
Visitor A
First-time visitor
Fulcrum saw
First pageview, no history
BASELINE
1
Dress Watch, Blush and Rose Gold
Why: Tote buyers choose this watch more often.
2
Oversized Sunglasses, Blush Tortoise
Why: Often bought after this tote.
3
Leather Espadrille Wedge, Tan
Why: Most common next category for tote buyers.
4
Midi Shirt Dress with Slit
Why: Most common apparel purchase for tote buyers.
Visitor B
Bought the same watch in the spring
Fulcrum saw
Order history - Dress Watch, Blush and Rose Gold
1
Oversized Sunglasses, Blush Tortoise
Why: First after removing the watch.
2
Leather Espadrille Wedge, Tan
Why: Most common next category for tote buyers.
3
Midi Shirt Dress with Slit
Why: Most common apparel purchase for tote buyers.
4
Diana Top Handle Crossbody Bag, Camel
Why: Most common second bag for this cohort.
Change: The watch drops out because it was bought in the spring. The crossbody takes its place because customers who own this tote and watch buy a second bag more often than anything else.
Visitor C
Espadrille wedge already in the cart
Fulcrum saw
Cart - Leather Espadrille Wedge, Tan
1
Dress Watch, Blush and Rose Gold
Why: Tote buyers choose this watch more often.
2
Oversized Sunglasses, Blush Tortoise
Why: Often bought after this tote.
3
Midi Shirt Dress with Slit
Why: Most common apparel purchase for tote buyers.
4
Fully Adjustable Casual Belt, Black
Why: Most common accessory added with the wedge.
Change: The wedge drops out because it is already in the cart. The belt takes its place because it is the accessory most often added to a basket holding the wedge.
This algorithm uses customer purchase behaviour, not product attributes. It finds cross-category relationships that are difficult to define manually. It never spends a slot on something the visitor already owns.
Viewed together
Products visitors view in the same session
This algorithm reads which products visitors view in the same session, not what they buy. Products most often viewed with this necklace rank highest. Products this visitor has already compared are removed so the row keeps moving.
Anchor product
Swiss Blue Topaz Station Necklace
$128.00
- Necklace
- Sterling silver
- Swiss blue topaz
- Bezel setting
Visitor A
First-time visitor
Fulcrum saw
First pageview, no history
BASELINE
1
Blue Topaz Bezel-Set Stud Earrings
Why: Most often opened with this necklace in a session.
2
Blue Topaz Leverback Drop Earrings
Why: Earring style visitors compare with the studs.
3
Tonal Blue and White Topaz Bracelet
Why: Frequently viewed with this necklace in a session.
4
Blue Topaz Ring, Silver and 14k Gold
Why: Viewed less often with this necklace.
Visitor B
Already compared both earring styles
Fulcrum saw
This session - studs, then drops, then back
1
Tonal Blue and White Topaz Bracelet
Why: First after both earring styles were viewed.
2
Blue Topaz Ring, Silver and 14k Gold
Why: Viewed less often with this necklace.
3
Cushion-Cut Swiss Blue Topaz Pendant Necklace
Why: Necklace visitors open next after the earrings.
4
Sterling Silver Cuff Bracelet
Why: Entry-price piece from the same sessions.
Change: Both earrings drop out because this visitor already opened them side by side this session. The pendant and cuff fill their slots.
Visitor C
Owns the bracelet, opened the ring twice today
Fulcrum saw
Order history plus two views of the ring
1
Blue Topaz Ring, Silver and 14k Gold
Why: First after two views in this session.
2
Blue Topaz Bezel-Set Stud Earrings
Why: Most often opened with this necklace in a session.
3
Cushion-Cut Swiss Blue Topaz Pendant Necklace
Why: Necklace most often compared with this one.
4
Sterling Silver Cuff Bracelet
Why: Bracelet the visitor does not already own.
Change: The bracelet drops out because it is already owned. The ring moves to the front after two views today, and the cuff fills the open slot.
Session co-viewing is available as soon as a product goes live because it uses browsing behaviour, not completed orders. Products the visitor has already opened or owns are removed before ranking.
- 8
-
Algorithms, live from day one
Every
customer - 24h
-
From new product to live recommendation
Nightly
recompute - 0
-
Empty recommendation
slots Waterfall
fallback - 0
-
Pixels to
maintain Server-side
integration
Freshness
Individual algorithms tuned every 24 hours for optimization.
Every night, Fulcrum rereads the entire product structure of your e-commerce store as well as inventory and applies the new behaviors seen that day from users based on purchases, product views, etc. All this information is used to constantly fine-tune the algorithms that are delivering personalized experiences and product recommendations to every user on your site every day.
Trust
The holdout is the guarantee.
A small, fixed 10% of your traffic never sees personalization - for the entire length of your contract. Comparing that group against everyone else, at the end of your 12-month term, is the entire basis for your guaranteed number.
Runs continuously for the full contract term, not a one-time test.
Calculated once, at the end of the term, using the conservative lower bound of the result.
This is the number behind your guarantee. See the guarantee .
Getting live
Getting live is the easy part, fully managed by Fulcrum.
Connection, configuration, and design review all happen before you ever see a change on your site, so what goes live is already approved, tested, and ready.
-
Connect
A first-party, server-side integration on Shopify Plus or BigCommerce. No pixels, nothing new for your team to maintain.
-
Configure
We apply the full algorithm suite to your catalog and purchase history. Every recommendation type, live from day one.
-
Review and approve
You see exactly where and how recommendations will appear across your site before anything goes live.
-
Go live, then stay current
Every surface activates together, and the entire suite rebuilds itself overnight from there on, so what visitors see always reflects your latest catalog.
Common questions
How the measurement actually works.
How is the guarantee measured?
It is based on holdout lift: the difference in revenue per user between personalized traffic and a fixed 10% randomized holdout that never sees personalization. We calculate it once, at the end of your 12-month term, at a 95% confidence level, and guarantee the conservative lower bound.
What exactly are you counting?
We measure one thing: the difference in revenue per user between your holdout group and everyone else over the full term. Your guaranteed figure is the conservative lower bound of that range, not a raw total.
How do you know the holdout is trustworthy - couldn't you just call it 'significant' whenever you want?
There is no interim evaluation. We calculate the lift exactly once, at the end of the 12-month term, at a 95% confidence level. A result qualifies when its lower bound is above zero.
Does recommendation freshness cost extra?
No. Pricing is based on monthly unique visitors, which is separate from the outcome guarantee. The nightly recompute and full algorithm suite are included at every tier.
What's the difference between what you show me and what you guarantee?
There is one number now. The holdout lift IS the guarantee basis - the holdout is not a separate check on some other figure.