We audit the shelves of digital stores.
AVBR Lab is an independent nonprofit research lab auditing algorithmic bias in e-commerce recommendation systems: what algorithms push, whom they show, and whom they leave out.
A nonprofit research lab
American Visual & Behavioral Research Lab Inc. — a California nonprofit public benefit corporation founded in February 2026. Independent of platforms, vendors and merchants.
Two platforms measured from the outside with one open protocol. Shopify sampled, BigCommerce taken as a census; seasonal and longitudinal waves pre-registered.
Two articles in preparation for JTAER; anonymized datasets deposited on Zenodo with DOIs — September 2026.
PublicationsPrice steering by seed-price band.
How much pricier are recommendations than the product being viewed? Mean price delta of recommendations, % above the viewed product, by the price band of the seed product.
The cheaper the product a shopper starts from, the harder the algorithm pushes them toward pricier recommendations.
Replicated across two platforms: the direction and shape reproduce; between-category differences do not.
Anatomy of a recommendation block.
The block is the unit of analysis. Every metric in the protocol is computed on one of these four layers.
Product page (seed)
Three seeds per store — popular, unpopular, median-priced. The page a shopper actually lands on, opened without login.
Recommendation block
Located by heading patterns with a structural fallback. The unit of analysis: every metric is computed here, the store is the cluster.
Price layer
Mean price of the recommended items against the seed. Winsorized to [−100%, +200%]; the gradient by seed-price band is the central finding.
Image & alt-text layer
Who appears on the cards (fashion and beauty, coded against the published codebook) and whether a screen reader gets anything at all.
Four waves. One protocol.
Recommendation algorithms quietly shape billions of purchase decisions, yet almost no one audits them from the outside. Our program makes the algorithmic shelf of online retail measurable, comparable, and accountable — platform by platform, year by year.
Shopify
300 stores surveyed, 221 analyzed. Price steering, popularity bias, brand concentration, representation, accessibility.
BigCommerce
Cross-platform replication on 1,394 candidate stores, 1,014 analyzed. First results confirm the Shopify pattern.
Seasonal slice
Black Friday snapshot: do recommendation systems collapse onto a narrow set of doorbusters?
Longitudinal wave
Same stores, six months later. Pre-registered design. Does the steering gradient persist?
Three rules we don't break.
No platform cooperation
We audit from the outside — the way a shopper meets the shelf. No API access, no partnerships, no permission required. Any researcher can rerun the measurement.
Open protocol
Sampling rules, seed selection, capture procedure, metric definitions and the visual-representation codebook are published on GitHub under CC BY 4.0.
Open data
Anonymized datasets are deposited with DOIs (Zenodo) alongside each publication. Capture losses are reported, never silently dropped.
Zenodo DOIs — September 2026
Rerun the shelf yourself.
The protocol, codebooks and datasets are open. Take the measurement to a platform we have not reached yet — or write to the lab.