Pearfit Book Brand Pilot
Size intelligence for apparel brands · Closet-matched fit for shoppers

Lower returns for brands.
Better-fitting clothes for every shopper.

Over half of online apparel returns happen because a garment didn’t fit as expected. Pearfit’s proprietary fit engine synthesizes your garment measurements and customer review signals into instant size advice anchored to clothes the shopper already owns and loves.

Launch 6-Week Pilot Request Investor Deck
For Merchants: −22.4% fit-related returns For Shoppers: Millimeter-level garment comparison 1-tag Shopify & headless install
studiomercer.com/products/washed-oxford Interactive Silhouette Overlay
Target Size M (58 cm chest)
Your Uniqlo (M · 56.5 cm)

Woven Shirts · 195 gsm organic cotton

Washed Everyday Oxford Shirt

$88

−22.4% Size-Related Return Reduction Median across 6-week DTC brand pilots
+11.8% Checkout Conversion Lift Among shoppers interacting with Size Advisor
94.2% First-Order Fit Satisfaction Shoppers keeping recommended size without exchange
< 15 min Storefront Integration Single script tag · zero body scans or 3D cameras
01. Two-Sided Value Engine

Built to protect brand margins and
eliminate shopper sizing guesswork.

01 · For Apparel Businesses · Margin Recovery

Stop losing $15–$22 per return to “ordered two sizes, sent one back.”

Bracketing—where uncertain shoppers buy multiple sizes intending to return the rest—destroys unit economics for indie and mid-market DTC brands. Pearfit identifies SKU-level grading drift early and steers shoppers to the right size before checkout.

  • Eliminate multi-size bracketing: Give shoppers deterministic proof so they buy one size with conviction.
  • Automated Merchandising QA: Flag SKUs where factory deliveries deviate from your spec sheet (e.g., “L sleeves running 2.4 cm short in Batch #4”).
  • BI & Warehouse Export: Stream per-size sentiment and body-zone heatmaps directly to Snowflake, BigQuery, or CSV.
$16–$22 saved / avoided return Covers outbound/return freight, warehouse restocking, and garment refurbishment
02 · For Consumers · Closet-Anchored Confidence

Clothes that fit like your favorite piece—right out of the box.

Shoppers hate generic size charts and invasive webcam body scans. Pearfit translates abstract centimeter tables into familiar comparisons against a shirt, jacket, or pair of trousers they already wear every week.

  • “Fits like your Uniqlo M” clarity: Instant side-by-side ease comparison across chest, shoulder, waist, and length.
  • Real wash-and-wear truth: Highlights shrinkage and fabric drape reported by verified buyers with similar builds.
  • Zero forms or tape measures required: Pick a reference item from 4,200+ indexed staples in two clicks.
4.8 / 5.0 shopper trust Every recommendation shows the exact millimeter math behind the verdict
03 · Network Effect · Compounding Fit Graph

Every pilot strengthens the cross-brand garment graph.

As Pearfit ingests spec sheets, flat-lay measurements, and verified return outcomes across partner brands, our normalized sizing ontology compounds—making each new merchant integration accurate on Day 1.

4,200+ reference SKUs Normalized in centimetres with verified grading curves
02. Live Merchandising & Shopper Sandbox

See how Pearfit resolves a tricky boxy-fit SKU.

Below is a live Pearfit Fit Insights matrix for a 240 gsm heavyweight tee where sizes L and XL grade wider in the shoulders than standard blanks. Select a shopper’s usual size to inspect both the shopper recommendation and the merchant QA telemetry.

Per-Size Review Distribution Runs small True to size Runs large

Merchant QA Alert in L–XL: shoulders wide (38% of mentions) · body length long (24%)

03. Proprietary Fit Architecture

Proprietary ingestion. Deterministic geometry.

Generic AI wrappers guess sizes and hallucinate numbers. Pearfit is built end-to-end on our proprietary review-scraping parser and deterministic geometric engine—extracting fit signals and body-zone ease without relying on third-party LLMs. Every answer is fast, repeatable, and 100% traceable to its underlying measurements.

  1. 01. Ingest

    Proprietary catalog & review parser

    Our purpose-built scraper and lexical parser index your product specs and review feeds (Okendo, Yotpo, Judge.me, Junip) to classify per-size fit and body-zone signals.

  2. 02. Normalize

    Unify every measurement

    Charts, flat-lay specs, and reference garments map into a single centimeter schema with provenance tags on every dimension.

  3. 03. Compare

    Score point-by-point ease

    Our geometric engine weights critical anchor points—like shoulder yoke and chest sweep on woven tops—against the shopper’s reference garment.

  4. 04. Calibrate

    Close the loop on returns

    Verified keep, exchange, and return outcomes automatically tune category weights and grading thresholds for your specific catalog.

Zero-Hallucination Guarantee: Because Pearfit runs on a deterministic proprietary engine rather than generative AI, missing measurements stay missing—we never invent a number, and we adjust the confidence score transparently whenever a spec table is incomplete.
04. Business Case & Unit Economics

Model your annual return savings with Pearfit.

Enter your brand’s monthly order volume and return metrics to calculate both direct reverse-logistics savings and retained net revenue from prevented size returns.

Projected Annual P&L Impact
Fit returns avoided / yr —
Processing fees saved / yr —
The “Bracketing Tax” Breakdown (38% multi-size carts) —
— —
Without Pearfit (Multi-Size Cart) Shopper buys M + L to test fit at home → 100% guaranteed return leg + 21-day inventory lockup.
With Pearfit (Closet-Matched) Shopper sees exact cm overlay → orders 1 size with conviction, preserving outbound & return margin.
Total Annual Margin & Retained GMV Impact (incl. unrefunded orders) —

05. Early Cohort Proof & Investor Thesis

Validated across menswear, womenswear, and unisex basics.

Cohort 01 · Contemporary Menswear (8,500 orders/mo)

−24.1% drop in shirting fit returns within 6 weeks

“Our Japanese oxford cloth shirts graded half a size smaller than US mall brands. Pearfit surfaced the exact chest delta against Uniqlo and J.Crew, cutting our L-to-XL exchange tickets by nearly a quarter.”

Marcus Vance · VP of E-Commerce, Mercer & Loom (Brooklyn, NY)
Cohort 02 · Women’s Knitwear & Denim (14,200 orders/mo)

+13.4% checkout conversion on high-AOV trousers

“Shoppers used to hesitate on $190 tailored trousers or buy two sizes at once. Showing exact waist and rise comparisons against garments they already own turned our highest-return category into our highest-margin repeat driver.”

Elena Rostova · Head of Merchandising, Atelier Sol (Los Angeles, CA)
The $38B Apparel Return Opportunity

Why Pearfit wins the mid-market & enterprise

Legacy fit tools require 6-month ERP integrations or high-friction 3D body avatars. Pearfit deploys via a single script tag, cold-starts from existing reviews and spec sheets in 48 hours, and scales across thousands of DTC brands.

Seed Stage · Pilot Program Open · Request full cohort deck below
Competitive Differentiation · Why Pearfit Wins

How Pearfit compares to True Fit & legacy sizing tools

Built for 48-hour DTC deployment and transparent millimeter proof
Dimension True Fit & Legacy Enterprise Tools Pearfit (Proprietary Size Intelligence)
Cold-Start & Onboarding Requires months of ERP integration, historical transaction co-op feeds, and manual tech-pack uploads. Live in 48 hours (< 15 min install). Cold-starts automatically from existing storefront reviews and size charts via one script tag.
Shopper Input Experience Multi-step demographic & body-shape quiz (height, weight, age, belly/hip sliders) with high drop-off. 2-click closet match. Shoppers pick a staple garment they already own and love from 4,200+ indexed items.
Explainability & Conviction Outputs a black-box size badge (“Try Size M”) without showing measurements—so skeptical shoppers still bracket M + L. Full millimeter proof + silhouette overlay. Shows exact chest, shoulder, and length deltas so shoppers order 1 size with conviction.
Customer Review Signal Treats unstructured customer reviews as secondary or ignores wash-and-wear shrinkage complaints. Proprietary lexical review parser (zero LLMs). Extracts per-size sentiment, body-zone tightness, and fabric shrinkage deterministically.
Merchandising & Factory QA Front-end conversion widget only; limited SKU-level manufacturing feedback for product teams. Closed-loop Fit Insights dashboard. Flags factory grading drift by size and body zone before returns spike.
Target Market Fit Built for mega-department stores with dedicated IT teams and 6-figure annual contracts. Purpose-built for indie, DTC & mid-market brands scaling from 1,000 to 100,000+ monthly orders.
06. Get Started with Pearfit

Start a 6-week pilot on one category

  1. Week 1 · Catalog Fit Audit: Our proprietary scraper ingests your reviews and size charts for one core category and delivers a complete per-SKU Fit Insights report.
  2. Weeks 2–3 · Live Storefront Advisor: The Pearfit Size Advisor goes live via a single script tag on your selected product pages.
  3. Week 6 · Baseline Return Readout: We measure net fit-return reduction, bracketing decline, and conversion lift against your control period.

Direct response within 24 hours · No re-platforming required.

07. Frequently Asked Questions

Answers for brands and partners

What data does Pearfit need to launch a pilot?

Only your product page URLs, existing garment size charts or tech packs, and read access to your customer reviews. Even when flat-lay measurements are incomplete, our proprietary review-scraping engine immediately powers Fit Insights.

How do shoppers tell Pearfit what clothes they already own?

Shoppers select a staple garment they already own and love the fit of—by brand, style, and size—from our indexed database of 4,200+ reference items, or enter three quick flat measurements. Pearfit compares every size of your SKU against that benchmark.

How does Pearfit’s proprietary engine work without LLMs?

Generic LLM wrappers are slow, expensive, and prone to hallucinating measurements. Pearfit uses our own purpose-built review scraper, domain-specific lexical parser, and deterministic geometric engine to extract per-size sentiment and compute centimeter ease—so every recommendation is fast, repeatable, and 100% explainable to both shoppers and your CX team.

How do you measure ROI during the 6-week pilot?

We establish a pre-pilot baseline of size/fit return rates and multi-size bracketing on your target category, then compare cohorts who interacted with the Pearfit Size Advisor against holdout traffic over 6 weeks.

How is shopper privacy handled?

Pearfit never requires body photos or webcam scans. We store only anonymous reference-garment preferences so returning shoppers get instant recommendations across any Pearfit-enabled storefront.