A little maths behind your size.
You get a suggested size and a match score. FRPPR uses one of two methods, depending on the chart available.
1. Store and standard charts: starting with your measurements
The store assistant works with body-measurement charts: chest or bust, waist and hips, in centimetres. Don’t know those numbers? FRPPR estimates them from height, weight and BMI using regressions calibrated against common retail charts, separately for women and men. Body shape (slim, athletic, curvy, fuller) adjusts individual measurements by a few centimetres. Waist estimates also increase slightly after age 40.
2. Comparing the sizes
We compare each measurement with the range for every size. To get d, we divide the distance from the middle of the range by half its width:
- Inside the range (
|d| ≤ 1) the penalty isd²— gentle. - Outside it the penalty is
1 + 4·(|d| − 1)— steep, so sizes that contain you win. - Chest/bust carries full weight, waist 0.85 and hips 0.8. On charts that list only height and weight, weight carries full weight and height 0.4, because height decides length and weight decides width.
Room to move. A body that sits in the last quarter of a size's range feels tight in it. So before scoring, FRPPR adds a comfort margin to chest, bust, waist, hips and weight: a quarter of the chart's typical size range, between 0.5 and 2.5 cm (or kg). In practice, if you fall in the last quarter of a size you are offered the next one up, and an exact tie goes to the larger size. The explanation under your result shows this as “+ room to move”. Comparing two garments you own skips the margin, because both already include their own room.
Fit preference changes width only, never length, height or weight: fitted −2 cm, relaxed +4 cm, on top of the comfort margin. If you tell us your usual size, rows away from it get an extra penalty of 1.6 × (steps away)², because a size you actually wear is stronger evidence than a BMI estimate; when the result lands one size away from it, your usual size stays on offer as the alternative. When the runner-up is an adjacent size with a close score, FRPPR shows it as the “between sizes” alternative.
3. Local brands: making sense of their charts
Upload a photo of the brand’s own chart and an AI model reads its sizes, measurement ranges, units and whether it measures the body or the garment. We keep the table, never the photo. Next, inches become centimetres and flat (half-width) garment measurements are doubled. We subtract the usual wearing ease for the garment’s category and cut. That gives every chart the same starting point: body measurements in centimetres.
When the chart doesn't say what it measures — true of most local-brand tables — FRPPR decides from the numbers, because reading a garment chart as body measurements recommends a garment with no room in it, one or two sizes too small. Widths too small to go around an adult body (up to 70 cm for chest or hips, 50 cm for the waist) are half-widths and are doubled. A length or shoulder column, or single values at least 5 cm above the standard body measurement for that size label, mark a garment chart. Ranges such as 96–100 mark a body chart. Charts you saved earlier are re-read with the current rules each time they are used.
Your body numbers start from the height-and-weight estimate above, then move toward the sizes you wear in brands you know: 75% your known size, 25% the estimate — or 85/15 when the two disagree by more than 8 cm. The scoring in section 2 then picks the size. Charts that only list height and weight are matched on those directly; there, fit preference moves you to the neighbouring size only when you fall between two.
Your own fit reports come first. When you tell FRPPR how a size you bought fit, that verdict becomes the strongest evidence for that category: just right places you in the middle of that size, too tight a quarter of its range past the top, too loose a quarter below the bottom. Up to your three latest reports per measurement are averaged and used as they are, without being pulled back toward the height-and-weight estimate. They tune only your own recommendations.
Brands that run small or large. When at least four shoppers have reported on a brand and category and 60% or more of them say it came out tight (or loose), FRPPR moves the recommendation about half a size: 3 cm for chest, bust and hips, 2.5 cm for the waist, 4 kg on weight-based charts.
4. Shoes
Your usual EU size becomes a foot length using the Paris-point relation foot ≈ EU ÷ 1.5 − 1.5 cm, then it is matched to the chart's foot-length ranges. Stores can mark their shoes as running small or large, which shifts the foot length by one size (≈0.66 cm); without a store setting, a shoe brand most shoppers report as small or large moves about half a size (≈0.33 cm). Shoes get no comfort margin.
5. What the match score tells you
The match score combines how well the best size fits (e^(−score)), how clearly it beats the runner-up, and whether it agrees with your usual size. In the size translator it rises when the chart's measurements come from sizes you know, and drops for garment-measurement charts and height-and-weight-only charts. It is clamped between 51% and 97%. This is an internal ranking heuristic, not a calibrated probability or an independently measured fit-accuracy rate.
6. Picking the size on the store page
The assistant recognises dropdowns, radio groups and size buttons. It reads labels such as “Medium”, “M”, “وسط” and “EU 42.0” in a consistent way, so it can match your suggested size and select it for you.
What the numbers can’t tell us
Height and weight only tell us part of the story. Add a size you already wear, the store’s own measurements or how a size you bought actually fit to improve the estimate. Unusual cuts, stretchy fabrics and oversized styles can still fit differently from what their charts suggest.
Prepared by the FRPPR team. Last reviewed: 12 October 2026.