Structural discovery of combinations

Your catalog's winning bundles.
With a fraction of the testing.

JEM finds your best kits, bundles and baskets while testing far less. Not a guess: it's proven mathematics — the computation is exact and checked on every run.

−75% fewer tests◆ math with a guaranteea diagnosis with an exit ramp

In plain words

What we do, without the jargon

Imagine you run a store and want to sell bundles — say "grab banana + strawberry + granola". The problem: there are hundreds of possible combinations, and finding out which one sells best means testing with real customers, which costs money.

We analyzed 3 million real purchases from a supermarket and found two things:

1

What makes a bundle sell is the combination, not the products

Some items go together (banana and avocado sell together all the time) and some never do (regular banana and organic banana — the customer picks one or the other). The tools companies use today score each product on its own and see none of this.

2

We built math that learns those combinations very fast

Every test of one bundle teaches you something about all the similar ones. The result: you can find the winning bundles with a fraction of the testing — in our simulation on this real data, about 8× less.

Important: this supermarket analysis is just one example of the application — the same method works for any catalog (delivery combos, menus, ad sets). And it's not guesswork: the math behind it is grounded and proven. A theorem guarantees it extracts the most signal possible from the data — for the kind of reconstruction it does, it's the best possible; there's no better version.

Less testing = less money burned on bad bundles and an answer fast enough to reach Black Friday with the right bundle. That's what we're selling to stores.


The problem

Testing combinations is costly — and the count explodes

A bundle's value is in the combination, not the loose items. But the number of combinations grows far too fast to test one by one on real traffic.

10120
products → possible 3-item kits
201.140
products → possible 3-item kits
304.060
products → possible 3-item kits

Every session spent on a losing bundle is money you don't get back. And picking "by gut" usually leaves the champion out.


How it works

Each test teaches you about many bundles at once

Instead of treating each bundle as an isolated test, JEM uses the structure of the combinations to get the most out of every observation.

Bundles that share items share information

Overlapping bundles are connected. One observation on a bundle already informs every other bundle that shares products — no starting from scratch each test.

We split the signal into layers

How much comes from each item, each pair (the synergy) and each trio. The champions almost always live in the pair.

Exact mathematics, not guesswork

The computation is provably exact — checked to machine precision on every run. No training, no GPU, no manual tuning: it runs in seconds over a spreadsheet.


What sets it apart

"If a bundle were just the sum of its items, you wouldn't need a bundle."

Models that score product by product stall before the best bundles — they're blind to exactly the synergy between items. JEM sees precisely the part they miss.

In the market baskets we measured, the biggest share of what makes a good bundle sits in the synergy layer — the band ordinary models can't represent.


Results

Fewer tests, the right bundles

Simulation and diagnostic figures, measured on real market data.

−75%
less test traffic to find the best bundles (in simulation)
−88%
in a simulator calibrated on 3.2 million real orders (Instacart)
21–75%
of the basket signal is beyond the reach of ordinary models
~10⁻¹³
computation error — machine precision, checked on every run
The final proof of revenue is always a pilot on your own traffic — these numbers show the method's efficiency and the structure of the problem, not a sales promise.

Where it fits

Where the value is in the combination

Rule of thumb: it pays off where the decision is about a set — and testing burns traffic or budget.

Promotional kits and baskets

Holidays, sales, Black Friday.

Marketplace & delivery combos

Build the combo customers actually want together.

Creative sets

Which trio of ads works best together.

Storefronts & collections

Assortment for pages and digital shelves.

Subscription kits

Pricing bundles and combined plans.

Recurring baskets

Replenishment and repurchase together.


How it starts

A 3-week diagnosis — with an exit ramp

We measure, on your historical data, how much synergy exists and how much your current process leaves on the table. It ends in a go/no-go.

If there's no meaningful synergy, we'll tell you — and you don't go further. No integration and no personal data: a simple history export is enough.

Find out what synergy is worth in your catalog

Fill this in and we compose a ready-to-send email — a 30-minute chat, no commitment.