Nykaa
ML-driven product recommendation + personalized retargeting
Nykaa multiplied its sales by 7.5, raised its average order value by 54%, and its media ROI by 1.7 through personalized product recommendation and retargeting driven by machine learning.
Key points
- ML-driven personalized product recommendation and retargeting.
- Criteo Engine for intent scoring, plus an in-house recommendation engine.
- Sales x7.5, average order value +54%, media ROI x1.7.
- Evidence B, confirmed status.
Objective
Bring mobile shoppers back to purchase and raise the average order value by pushing the right products at the right time through ML-driven recommendation and retargeting.
The deployment
Nykaa, an Indian beauty platform, uses product recommendation and dynamic retargeting to engage its shoppers on the app and mobile web. The Criteo Engine draws on a large data pool to estimate purchase propensity and identify the most relevant products, then serves personalized ads in the shopper's preferred format. In parallel, Nykaa is building its own recommendation engines (purchase history, browsing, skin type) and is moving toward a genAI use of personalization, covered by the beauty press.
Results Proof B
Quantified platform case study (Criteo) with a quote from Nykaa's CMO, complemented by the established beauty press (BeautyMatter) on the brand's AI personalization.
How it works
Inferred typical approachThe internal detail is not public. Here is a proven approach that leads to the same result, to adapt to your stack.
The stack in detail
- plateforme Criteo Engine Criteo's ML engine that estimates purchase propensity from a large pool of behavioral data and selects the most relevant products for each shopper.
- outil Retargeting dynamique Criteo Delivery of personalized ads in the shopper's preferred format, on app and mobile web.
- outil Moteur de recommandation Nykaa Nykaa's proprietary ML for on-site recommendation, based on purchase history, browsing, and skin type. Exact models not published.
How it runs, concretely
For ops teams-
1Signal collection site/app + data team
Browsing, searches, cart additions, and purchases feed the data pool.
-
2Intent scoring AI (Criteo Engine / Nykaa recommendation)
The ML engine estimates purchase propensity and the most relevant products.
-
3Personalized delivery AI + media team
Retargeting ads and recommendations are pushed in the shopper's preferred format.
-
4Purchase customer
The shopper returns to the app/web and converts.
-
5Optimization marketing / data
The growth team adjusts budgets, audiences, and product feed based on performance.
The flow of behavioral data (browsing, cart, history) and a clean product catalog. If tracking or the product feed degrades, recommendation loses relevance and retargeting becomes noise.
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
- clean, up-to-date product feed
- consented behavioral tracking
- first-party purchase history
Org prerequisites
- performance marketing team
- consent management (especially in the EU)
- media budget
Possible stack
- Criteo
- recommendation engine (Algolia, Dynamic Yield, Bloomreach)
- in-house ML recommendation
The plan, step by step
- Step 1Make the product feed reliable (price, stock, images, attributes) and verify that behavioral tracking is consented and complete across app and web.Deliverable: Validated catalog feed + GDPR-compliant tagging plan
- Step 2Connect the retargeting/recommendation platform to the feed and tracking, and define the highest-intent segments (cart abandoners, repeat PDP visitors).Deliverable: Campaigns configured on 2-3 pilot segments
- Step 3Launch the test with a framed media budget and a control group, measuring attributed sales, average order value, and media ROI.Deliverable: First performance read vs control
- Step 4Extend to the other segments, adjust budgets, audiences, and product feed based on performance, and turn on on-site recommendation.Deliverable: Extended setup with documented optimization rules
First step: Make the product feed and consented tracking reliable, then turn on a recommendation/retargeting engine on the highest-intent segments.
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 Nykaa - Criteo Success Story Interested party archive pending
- S2 Nykaa and the Rise of India's Beauty Economy Established press 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.