~ / how it works

How the ranking engine works.

No black box. You choose the signal, QSortby scores your catalog in real time and keeps in-stock first — or personalizes per shopper — then proves the lift with a built-in A/B test and revenue attribution. Here’s the inside.

Step 1 · Choose

10+ signals to rank by.

Set the rule per collection, over a window you pick — a rolling last N hours/days, or a fixed range like last week or a specific month. Change it anytime; preview before it goes live.

Sales

Rank by what sells

Best selling (velocity) — Units sold over your window — the classic top-seller.
Top revenue (GMV) — Summed order value, so high-ticket products rank on the money they make, not just unit count.
Most profitable (margin) — Product margin — lead with what actually earns.
Customer favorites — Repeat-purchase rate — the products buyers come back for.

Momentum

Catch what’s moving now

Trending / rising — Sales this window vs. the one before it — surfaces accelerating products, not last season’s hits.
Selling fast — Velocity relative to remaining stock — what’s about to sell out rises first.

Engagement & conversion

Rank by shopper behavior

Best converting — Conversion rate — the products that turn views into orders.
Most added to cart — Intent, one step before purchase.
Most clicked / highest CTR — What earns the click from the grid.
Longest dwell / most impressions — Attention captured on the page.

Catalog

Rank by product quality

Top rated — Bayesian review average, so a 5.0 from three reviews doesn’t outrank a 4.8 from three hundred.
Newest arrivals — Freshness — give launches their moment.

Step 2 · Rank

Scored live. In-stock first.

Re-scored on every order. Shopify order webhooks feed QSortby directly, so the ranking reflects sales within seconds — not a nightly batch.
Sold-out steps aside. Out-of-stock products are bucketed to the bottom automatically, and climb back to their earned spot the moment you restock.
Windowed & deterministic. The order is a transparent function of the signal + window you chose — no mystery. You can see the exact resulting order.
Preview before publish. Every change shows a before/after diff — added, removed, moved — so nothing goes live until you say so.

Standard Shopify collections. QSortby maintains native collections and a Best Sellers collection — no theme code, no custom storefront work.
Per-collection rules. Each collection can rank on a different signal and window — trending for new launches, conversion for candles, availability for seasonal lines.
Manual override. Reorder or exclude specific products by hand where you want an editorial call; the rest keeps sorting itself.

Step 2½ · Personalize

A "For You" feed per shopper.

Beyond one order for everyone, QSortby can render a per-visitor feed. Visitors are classified into types you define, and each type gets a ranking that blends weighted signals — a live, personal front row.

Visitor types you control. New, returning, loyal/VIP — each with its own weighting recipe.
Blended signals. Top-sellers, recently viewed, session intent, price affinity, category affinity, repeat / replenishment timing, new arrivals, return-rate.

First-party, cookieless. Built from behavior on your store only — no third-party data, no cross-site tracking.
Cold-start safe. A brand-new visitor still gets a strong best-sellers order while the feed learns.

Step 3 · Prove

How we answer "maximum conversion value."

You don’t have to trust the sort. QSortby runs it as an experiment and measures the money it actually drove.

Illustrative. QSortby splits visitors between your current order and the new sort, then reports the real funnel each drove.

Visitor-split A/B. Shoppers are deterministically split between control (your current order) and the QSortby sort — the same visitor always sees the same arm.
The full funnel, per arm. Impressions → clicks (CTR) → add-to-cart → orders, measured for each variant from a first-party pixel.

Revenue attribution. Orders are tied back to the QSortby feed a shopper interacted with, so you see influenced revenue per variant — not just clicks.
Statistical significance. QSortby won’t crown a winner on noise — it reports confidence, so you ship the sort the data actually supports.

Attribution is influenced / last-touch — it shows which sort a converting shopper engaged with, an honest directional read of lift, not a lab-grade incrementality study.

Data & privacy

Your data, used to rank your store.

First-party only. A pixel on your storefront — no third-party cookies, no cross-site tracking, nothing sold or shared.
GDPR-ready. Shopify’s data-request and redaction webhooks are honored; visitor data is purged on request.

Coarse by design. IP addresses are anonymized before storage; profiles are behavioral, not identity.
Shopify-native billing. Free 7-day trial, billed through Shopify’s Billing API on your normal invoice.

Talk to the team

See the engine on your catalog.

Book a 15-minute demo — we’ll screen-share the dashboard and run the experiment + attribution on your real collections.

Book a demo Add to Shopify