| Page type | Performance, before | Performance, after | Speed Index, before | Speed Index, after |
|---|---|---|---|---|
| Home | 30.0 | 52.0 | 17.2s | 9.5s |
| Product | 30.5 | 60.6 | 19.8s | 9.1s |
| Collection | 31.3 | 57.5 | 19.2s | 8.8s |
| Blog | 33.1 | 59.9 | 19.4s | 8.2s |
Audited June 12, 2026, Lighthouse 13.3.0, Moto G Power emulation with 4x CPU slowdown and slow 4G, matching Google's standard mobile testing conditions.
Sessions across these two windows were nearly identical (105,629 vs. 105,604), so the increase in orders and revenue is not explained by a change in traffic volume.
Confirms the site-wide result holds at the individual channel level, not just in aggregate.
| Channel | Rate change, 2026 | Rate change, 2025 | Improved |
|---|---|---|---|
| Paid Social, mobile | +334% | -21.8% | Yes |
| Organic Search, mobile | +4% | -8.8% | Yes |
| Direct, desktop | +51% | -31.4% | Yes |
| Organic Search, desktop | Flat | -15.8% | Partial |
| Direct, mobile | +55% | -39.1% | Yes |
| Unassigned, mobile | +99% | -29.4% | Yes |
| Paid Search, mobile | +9% | +44.6% | No, improved more last year |
| Paid Search, desktop | +34% | -12.1% | Yes |
Paid Search, mobile is the one exception: it improved last year as well, by a larger margin, so this method cannot attribute that specific channel's improvement to the optimization.
5 of 7 channels show a statistically confirmed increase exactly at the June 19 launch date, beyond any pre-existing trend, and a 6th shows a confirmed decrease, disclosed in the table below. Two of the five (Direct-mobile, Paid Search-desktop) have held up under every version of this test run to date.
Designed specifically to rule out "this was already trending in that direction." Most channels pass it.
Combined across all 7 tested channels, weekly-averaged conversion rate, Jan - Aug 2026.
| Channel | Baseline CVR | Actual change at launch | Confirmed |
|---|---|---|---|
| Organic Search, mobile | 2.73% | -29.4% | Yes, negative |
| Organic Search, desktop | 2.74% | -11.8% | No |
| Direct, mobile | 4.87% | +27.8% | Yes |
| Paid Search, mobile | 7.92% | +28.1% | Yes |
| Paid Search, desktop | 9.12% | +56.0% | Yes |
| Unassigned, mobile | 4.13% | +63.1% | Yes |
| Paid Social, mobile | 0.79% | +88.3% | Yes |
"Actual change" is the relative percentage shift at each channel's own baseline conversion rate right before the launch, not a raw point difference. Based on 223 continuous days of 2026 data with no gaps. "Confirmed" indicates statistical significance (p < 0.05), not simply that the number moved.
Optimisation 01 delivered a measurable conversion improvement: rate up 37%, revenue up 25%, orders up 37% on essentially flat traffic, ruling out volume as the cause.
It holds up under scrutiny: the same dates last year moved the opposite way, 6 of 8 channels reversed direction, and a trend-adjusted statistical test confirms an increase in 5 of 7 channels.