PPLOTTDATA
Rank → velocity

Turning search placement into an estimate of units

Wayfair never publishes unit sales. But cumulative review count is displayed on every listing, and the change in that count over a week is a direct function of how many people bought. Weekly snapshots convert a static number into a flow — and that flow, read against rank, is the relationship between placement and sales volume.

Visibility gradient, top-12 vs page 2
3.4×
Measured on the real cross-section, not assumed
Zero-review listings, top 12
1.4%
Almost every above-the-fold listing has review history
Zero-review listings, page 3+
19.8%
Where a listing without reviews begins
Review-rate band used
2–4%
Tunable — calibrate against your own Partner Home units

The measured visibility gradient

Median cumulative reviews by organic rank band, indexed to the page-2 band. This is the empirical relationship the velocity model is calibrated on.

Observed
The velocity layer

Estimated weekly units by rank band

Mean estimated units per SKU per week, derived from weekly review deltas at a 3% review rate. These rows come from the illustrative panel — the shape is calibrated on real data, but the levels become measured once collection has run for four weeks.

Mean new reviews per SKU per week

The measured signal underneath the unit estimate

Illustrative panel

Estimated units per SKU per week

new_reviews ÷ 3% review rate

Illustrative panel
Rank bandSKUsMedian new reviews/wkMean new reviews/wkEst. units (4% rate)Est. units (3% rate)Est. units (2% rate)
01-12 (above the fold)58121.83466191
13-24 (page 1 mid)52400.58151929
25-48 (page 1 tail)106910.81202740
49-72 (page 2)105300.42111421
73+ (page 3+)67700.17469
Daily grain

What the daily feed looks like

Organic rank trajectories for the top listings in Shoe Racks & Cubbies across 28 days. Rank 1 sits at the top of the axis. This is the shape of the ongoing feed — the final day is the real snapshot, the preceding days are illustrative.

Daily organic rank, Shoe Racks & Cubbies

One line per SKU · lower is better

Illustrative panel
Calibration

How to make this exact

The unit estimate divides weekly review deltas by an assumed review rate. An assumption is fine for ranking competitors against each other, but you can do better — and this is the single highest-value step available to SONGMICS HOME.

You hold Partner Home unit sales for your own SKUs. Give us one quarter of those against the same weeks of review deltas and we solve for your actual review rate, per category. That converts the proxy into a calibrated unit model — which we then apply to every competitor listing on the shelf, where you have no visibility today. Your own ground truth becomes the instrument that reads the rest of the market.