Loro Piana
Selling campaign fully automated by AI (audiences, placements, bids, creative combinations), remarketing and prospecting in a single campaign
In 2024, Loro Piana (LVMH) doubled its online purchases and cut its cost per purchase by 52% in the UAE by handing its selling campaigns to Meta's AI (Advantage+ Sales Campaigns), against its manual catalog structure.
Key points
- E-commerce selling campaign fully automated by Meta's AI in the UAE.
- Meta Advantage+ Sales Campaigns, Pixel and Conversions API, custom audiences.
- Twice as many purchases, cost per purchase -52%, cost per add-to-cart -13%.
- Evidence B, confirmed status: Meta case study on a test compared against the manual structure.
Objective
Sell more luxury products online in the UAE without multiplying manual campaigns: Meta's AI handles targeting and delivery, the team keeps control of the catalog and creatives.
The deployment
Loro Piana, the Italian fashion and cashmere house of the LVMH group, compared its former catalog campaign structure (manual targeting and segmentation) against Meta's Advantage+ Sales Campaigns mode. The principle: the advertiser provides the catalog and visuals (photo and catalog carousels, collection ads, photo ads), and the algorithm decides on its own the audiences, placements, bids and creative combinations, while covering remarketing and prospecting in a single campaign. The test targeted men and women aged 18 and over in the United Arab Emirates, with custom audiences of existing customers and site visitors. Over the period from March 7 to April 6, 2024, the Advantage+ campaign delivered twice as many purchases and a cost per purchase 52 percent lower than the manual structure, with a cost per add-to-cart down 13 percent.
Results Proof B
Official Meta case study, quantified, backed by a test comparing Advantage+ against the manual structure, with named people and agency; single source published by the platform, not corroborated by a primary or press source.
How it works
Documented architectureThe stack in detail
- plateforme Meta Advantage+ Sales Campaigns audiences, placements, bids and creative combinations driven by Meta's ML, prospecting and remarketing in a single campaign
- infra Meta Pixel + Conversions API reporting of purchases and add-to-carts, the signal the algorithm optimizes on
- outil Custom audiences Meta lists of existing customers and site visitors, used as value signals and for remarketing
- outil Formats catalogue Meta (carousel, collection, photo ads) the creative bank fed to the algorithm, which tests the combinations without human arbitration
- integrateur Spark Foundry (Publicis) media agency on the account, co-piloting the test comparing Advantage+ against the manual structure
How it runs, concretely
For ops teams-
1Provide catalog and creatives E-commerce / creative team
Product feed plus a stock of varied formats: photo and catalog carousels, collection ads, photo ads. The algorithm tests the combinations, the team does not pick the winner.
-
2Load the custom audiences Data / CRM team
Lists of existing customers and site visitors, used as value signals and for remarketing within the same campaign.
-
3Let the AI drive Meta AI
Advantage+ decides audiences, placements and bids, and combines prospecting and remarketing. Editing the campaign too often breaks the learning.
-
4Compare against the manual structure Media / agency team
The decision to switch was made on a test comparing Advantage+ against manual catalog campaigns, judged on cost per purchase and volume.
Purchases and add-to-carts reported by the Pixel and Conversions API. If this signal is incomplete, the algorithm optimizes on noise and the cost per purchase rises.
How your customers perceive this type of use
Sourced studiesLe pricing algorithmique est le terrain le plus inflammable : 68% des consommateurs disent se sentir leses quand les marques utilisent le pricing dynamique et 80% jugent plus dignes de confiance les marques aux prix constants (Gartner, 2024). L'equite percue varie selon le secteur : le pricing dynamique n'est juge juste que par 33% a 40% des repondants selon qu'il s'agit de concerts ou de cinemas (YouGov, 17 marches). Le prix personnalise par les donnees individuelles est le plus rejete : 47% des Americains s'y opposent fermement (Consumer Reports, 2024).
Acceptance conditions
- La constance des prix comme signal de confiance : 80% jugent plus fiables les marques aux prix stables (Gartner 2024)
- Le secteur conditionne l'equite percue : le pricing dynamique est mieux tolere pour les cinemas (40% le jugent juste) que pour les concerts (33%) (YouGov 2024)
Red lines
- Le pricing dynamique percu comme abus : 68% se sentent leses (Gartner 2024)
- Le prix individualise a partir des donnees personnelles : 47% d'opposition ferme (Consumer Reports 2024)
- Les frais caches et hausses imprevues, vecus par 79% des consommateurs sur un an et associes a la perte de confiance (Gartner 2024)
Sources: Gartner 2024 · YouGov 2024 · Consumer Reports 2024
How to replicate
Inference, not sourcedData prerequisites
- Clean and up-to-date product catalog (feed)
- Pixel + Conversions API with reliable purchase and add-to-cart events
- Customer and visitor lists for custom audiences and exclusions
Org prerequisites
- Multi-format creative bank (carousels, collection, photo)
- Accept letting the learning run without over-managing the campaign
Possible stack
- Meta Advantage+ Sales Campaigns + CAPI (server-side GTM or partner)
- Advantage+ campaign budget
The plan, step by step
- Step 1Make the product feed and measurement reliable: Pixel + Conversions API with verified purchase and add-to-cart eventsDeliverable: Clean feed + validated events in Events Manager
- Step 2Load the custom audiences (customers, visitors) and build the multi-format creative bankDeliverable: Active audiences + carousels, collection and photo ads ready
- Step 3Launch Advantage+ Sales alongside the manual catalog structure, on a share of the budgetDeliverable: Live comparative test, learning phase started
- Step 4Let it converge without editing the campaign, since each major change restarts 1 to 2 weeks of learningDeliverable: Campaign out of the learning phase, stable data
- Step 5Judge on cost per purchase and purchase volume against the manual structureDeliverable: Quantified decision to shift the catalog budget to Advantage+
First step: Launch a comparative test: an Advantage+ Sales campaign against the existing manual catalog structure, on 20 to 30 percent of the social budget, judged on cost per purchase.
The same pattern, proven in other industries
adidas
AI-driven audience prospecting and bidding (ARO) across the full funnel
Allwyn
AI-driven omnichannel programmatic buying with retail data activation
Nivea
genAI testing and optimization of creative elements + automated localization at scale
Sources
- S1 Loro Piana: Facebook ads case study - Advantage+ sales campaigns Interested party archive pending
- S2 Meta Advantage+ Sales Campaigns: AI Automated Shop Ads Interested party 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.