Neutrogena
AI skin diagnosis from a selfie leading to a product recommendation
Kenvue rebuilt the Neutrogena Skin360 skin diagnosis in 2025 with Haut.AI: analysis of a selfie on eight skin indicators, an overall score from 1 to 10, LIQA image quality control, and product recommendations, deployed in the United States and Canada.
Objective
Make the skin diagnosis the personalized entry point to the brand, with more accurate product recommendations to convert and retain across the Neutrogena channels.
The deployment
Neutrogena Skin360, launched in 2020, scans a selfie and scores skin health. In September 2025, Kenvue rebuilt the experience with Haut.AI. The new engine assesses eight skin indicators (hydration, smoothness, even skin tone, radiance, firmness, dark spots, wrinkles, clarity) and produces an overall Skin360 score rated from 1 to 10. The experience starts with Haut.AI's LIQA system, which guides the user to take a well-framed and well-lit selfie, a condition for a reliable analysis. The refresh brings an analysis engine with enhanced algorithmic accuracy, to identify individual concerns more finely and deliver more accurate product recommendations. The rebuilt experience is available in the United States and Canada via the Neutrogena brand sites and selected retail partners. Neutrogena notes that the tool does not replace a medical consultation.
Results Proof C
Refresh documented by a joint Haut.AI / Neutrogena press release naming the leads, and press coverage (Fortune, Drug Store News). Quantified product details (8 indicators, score 1 to 10) but no public business metrics, hence C.
How it works
Documented architectureThe stack in detail
- outil Haut.AI Computer-vision skin analysis engine: eight indicators (hydration, smoothness, evenness, radiance, firmness, spots, wrinkles, clarity) and an overall score from 1 to 10.
- outil LIQA (Haut.AI) Live Image Quality Assurance that guides selfie framing and lighting before analysis.
- plateforme Sites de marque Neutrogena (Skin360) Web experience hosting the scan, the score, and tracking over time, in the United States and Canada.
- outil Moteur de recommandation produit Mapping of the detected indicators and concerns to the Neutrogena catalog.
How it runs, concretely
For ops teams-
1Guided selfie framing AI (Haut.AI LIQA)
LIQA checks image quality live before analysis.
-
2Skin indicator analysis AI (Haut.AI)
The engine scores eight indicators and produces an overall score from 1 to 10.
-
3Product recommendation AI + e-commerce
The score and detected concerns steer toward Neutrogena products.
-
4Tracking over time user
The user redoes the scan to track how their skin evolves.
The quality of the captured image (framing, light) validated by LIQA. Without a usable image, the eight indicators are noisy and the recommendation loses its credibility.
How your customers perceive this type of use
Sourced studiesLe paradoxe est documente des deux cotes : 71% des consommateurs attendent des interactions personnalisees et 76% sont frustres quand elles manquent (McKinsey, 2021), mais 75% declarent ne pas acheter aupres d'organisations auxquelles ils ne confient pas leurs donnees (Cisco, 2024). La « creepy line » est localisee : messages recus quelques secondes apres une recherche et suivi de localisation sont les pratiques qui mettent le plus mal a l'aise (Periscope by McKinsey, 2019).
Acceptance conditions
- La confiance dans le traitement des donnees precede l'achat : 75% ne achetent pas sans elle (Cisco 2024)
- Un cadre legal protecteur rassure : 59% des consommateurs disent que des lois fortes sur la vie privee les rendent plus a l'aise pour partager des informations dans des applications IA (Cisco 2024)
- La personnalisation elle-meme est attendue quand elle est consentie : environ la moitie des consommateurs (US 55%, UK 52%) disent s'inscrire souvent ou parfois a des services personnalises (Periscope by McKinsey 2019)
Red lines
- Le message declenche quelques secondes apres une recherche ou un achat : deuxieme ou troisieme cause de malaise selon les pays (Periscope by McKinsey 2019)
- Le suivi de localisation percu comme de la surveillance : 40% de malaise en Allemagne et au Royaume-Uni (Periscope by McKinsey 2019)
- Le mesusage des donnees personnelles par l'IA, devenu la premiere inquietude des consommateurs, a 53% et en hausse (Qualtrics 2025)
Sources: McKinsey & Company 2021 · Periscope by McKinsey 2019 · Cisco 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- biometric consent and compliant image processing
- product catalog with skin attributes
- possibly a scan history for tracking
Org prerequisites
- integration into the e-commerce journey
- legal framing on the non-medical nature
Possible stack
- skin analysis API (Haut.AI, Perfect Corp, ModiFace)
- product recommendation engine
- brand CMS / e-commerce
The plan, step by step
- Step 1Frame the legal side (biometric data, explicit consent, non-medical nature) and choose the skin analysis API.Deliverable: Validated compliance file and signed API contract.
- Step 2Integrate the analysis API and the image quality control into the web or app journey.Deliverable: Working scan journey in pre-production.
- Step 3Map the skin indicators to the product catalog with recommendation rules validated by the brand.Deliverable: Indicators-to-products matrix in place.
- Step 4Launch on a page with high purchase hesitation and measure conversion and re-scan rate.Deliverable: Conversion / repeat-scan readout and expansion plan.
First step: Plug a skin diagnosis API into a product page with high purchase hesitation and measure conversion and repeat scan.
The same pattern, proven in other industries
Taobao
Real-time product recommendation with deep learning, served across hundreds of scenarios in the app
Amazon
Item-to-item collaborative filtering product recommendation engine, served across every touchpoint
ASOS
catalog-scale deep learning product recommendation, plus a conversational style assistant
Sources
- S1 Haut.AI Collaborates with Neutrogena on The Refresh of Iconic Neutrogena Skin360 with Advanced AI-Driven Skin Analysis Technology Interested party archive pending
- S2 Cosmetic companies are using face-scanning AI apps to create deeper connections with customers Established press archive pending
- S3 Neutrogena, Haut.AI collaborate on revamped Skin360 experience Secondary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.