Retail · Personalisation

Retail personalisation: one customer, one tone, every surface.

Unified personalisation across web, app, email, and in-store signage. Ensemble recommender plus contextual bandits — coherent, measurable, and respectful of consent on every surface.

personalisation · consoleLIVE
SURFACE · PRS-0918
PDP recommend · luxe beauty
Session 14m · 3 moisturisers viewed
SIGNAL CHECKS
Cohort matchpending…
Catalogue inventorypending…
Bandit confidencepending…
Price sensitivitypending…
Content variantpending…
CONFIDENCE
INTENT · ROUTING
4 products surfaced · CTR +42% vs baseline
Rendered to PDP · web + app · A/B logged
REASONING
Browsing pattern matches post-beach repair cohort · prioritise barrier
Cross-sell · serum + SPF set · margin-positive bundle
Seasonal modifier engaged · light-textured emulsions surfaced
OPTIMISING…
rendered · 4 slots

What we build

A personalisation layer that speaks for the brand — not a bolt-on that fragments it.

Each module is a production component — not a proof-of-concept — wired into your CDP, catalogue, and channel stack, with holdout-validated lift on every surface.

Recommendation engine across surfaces

Collaborative filtering + contextual bandits serve coherent recommendations on PDP, home rails, app, email, and in-store signage — same customer, same tone, every touch.

Personalised merchandising

PDP cross-sell, home-rail reorder, and category-page merchandising tuned per visitor — holdouts in place so lift is attributed cleanly to the personalisation layer.

Dynamic email + app content

Hero imagery, body copy, and product modules selected per segment at send time — winning variants promoted automatically through a managed bandit policy.

In-store signage feeds

Dwell-time signals and inventory-linked content feeds rotate signage per store, per hour — privacy-safe sensor counts only, no biometric capture anywhere on the floor.

RFV + wardrobe / fragrance modelling

Recency-frequency-value segmentation plus category-specific modelling — wardrobe continuity for fashion, fragrance-profile continuity for beauty, watch-collector cohorts for jewellery.

Ultra-luxury 1:1 curation

For the top-tier cohort, personalisation shifts to hand-curated lists reviewed by a stylist — the copilot drafts, the human edits, the client sees signature service.

Where personalisation earns its keep

Same layer. Different surfaces.

One feature store, one identity layer, one recommender — activated across every surface the brand owns. Category-specific modelling layered on top: wardrobe continuity for fashion, fragrance profile for beauty, occasion modifiers for jewellery.

01

Multi-channel retail brands

Brands running web, app, email, CRM, and physical stores — one unified personalisation layer across every surface, tuned per channel without fragmenting the profile.

02

Premium beauty · counters + D2C

Skin-routine continuity across visits, fragrance-profile matching, sampling-led nudges, and counter-linked signage — respecting the beauty consultation as a service moment.

03

Fashion · mass-affluent upwards

Wardrobe-based recommendations, capsule-launch orchestration, and look-led merchandising — with seasonal and occasion modifiers that align with the brand calendar.

04

Category pages + landing pages

Grid order and module copy tuned per visitor intent — search term, referral, and cohort signals blended with inventory for merchandise-right, conversion-right pages.

05

App home rails

Home-screen rails personalised per session — with bandit exploration so the system keeps learning without starving proven winners of distribution.

06

Lifecycle email + journeys

Behavioural and transactional streams personalised at send time — winback, post-purchase, replenishment, and VIP cadences running on the same model layer.

A walk-through

From one profile to every surface — in five clear steps.

Follow a real brand rollout through unify, model, activate, measure, and refine. Every step is visible to the merchandiser, the data office, and the brand director.

ANCHOR · VELVET RETAIL HOLDINGS
Velvet Retail Holdings· 14 markets · 620 stores · 8M CRM members · web + app + email + signage
STEP 01 · 05
STEP 01 · UNIFY
One profile across every surface
Web, app, email, in-store, and clienteling identifiers stitched into a single profile in the CDP — never a different person per channel.
CDP · UNIFIED PROFILES
real-time
Identifiers stitched11.7M profiles
Channels unified5 · all live
Match rate94.2% · cross-device
Consent recorded100% · per region
SOURCES PIPED
Web · Segment
12.4M events/d
App · mParticle
3.8M MAU
Email · SFMC
8.0M members
POS · Lightspeed
620 stores
One profile · same identity in app, on web, in store

Model families we deploy

No single model covers every surface. So we ensemble.

Each model family covers a distinct personalisation problem — blending their outputs gives you coverage, resilience, and a consistent tone every surface can trust.

MATRIX FACTORISATION + GRAPH
Collaborative-filter ensemble

Matrix-factorisation, item-item similarity, and graph-embedding models blended into a single ranker — resilient to cold-start and tunable to each brand's catalogue shape.

THOMPSON SAMPLING · Ε-GREEDY
Contextual-bandit policy

Per-surface bandit layer explores new variants while protecting proven winners — exploration budget tunable per brand and per surface to balance learning and lift.

RECENCY · FREQUENCY · VALUE
RFV segmenter

The classical retail segmentation, reframed for luxury and premium — value-weighted, cadence-aware, and refreshed daily so cohort routing stays current as clients move tiers.

CDP-AWARE ACTIVATION
Cross-channel sync agent

Keeps recommendations coherent across web, app, email, and signage — the same customer sees a consistent message, never a contradiction between the email and the PDP.

Data sources wired into every decision

The signals that power coherent personalisation.

Pulled in parallel, normalised into a shared feature store, and respected by every consent and residency rule before any surface sees a recommendation.

Source
What it unlocks
Providers
Web / app event stream
Real-time behavioural events — view, search, add, remove, purchase — piped into the feature store that drives ranker and bandit decisions on every surface.
SegmentmParticleRudderstackAmplitudeAdobe Analytics
CDP · identity + consent
The unified profile and consent ledger — without which personalisation becomes channel-by-channel fragmentation. Powers identity-stitching, match-rate reporting, and opt-out enforcement.
TealiumExponeaSalesforce Data CloudSegment UnifyAdobe RT-CDP
Email + journey platform
Lifecycle and campaign sends with dynamic content blocks and send-time bandit policy — attribution feeds back into the model layer so next-cycle variants start smarter.
Salesforce Marketing CloudBrazeKlaviyoIterableBloomreach
Product catalogue + inventory
Attributes, merchandising flags, and live stock — so the ranker never surfaces an out-of-stock piece and the bandit never promotes a variant the brand has de-listed.
PIM systemsSFCC catalogueInventory APIsReplenishment feeds
Digital-signage CMS
Store-level signage pipelines with schedule and content-template APIs — enabling dwell-linked rotation and inventory-aware creative swaps at the aisle level.
BrightSignSamsung VXTStratacacheBroadsignScala
In-store sensor / beacon data
Anonymous dwell, zone, and traffic signals — never biometric. Linked to signage and clienteling outputs, privacy-first and audited per jurisdiction's guidance.
RetailNextShopperTrakEstimoteAislelabsPassive Wi-Fi

Lift · attribution · provenance

A recommendation means nothing without the trail behind it.

Every decision is logged with its model, version, signals, and bandit policy. Every surface ships with holdout-validated lift. Every recommendation can be explained, audited, and — if the merchandiser says so — overridden.

  • Holdout groups maintained per cohort
  • Per-decision model + signal provenance
  • Bandit policy version tracked
  • Aligned to GDPR, PDPA, PIPL, CCPA, IAB TCF 2.2
DECISION RECORD · PRS-0918
reco.explain v3.4
SurfacePDP · web + app
Ranker pathensemble v3.4 · top-4
Bandit armarm B · 0.88 conf
Top signal 1view_seq_cosine · 0.31
Top signal 2cohort_rfv_v · 0.24
Consent stateTCF 2.2 · all purposes
Audit SHAc812…b394

Governance & consent

Personalisation worth the trust customers extend.

Consent enforcement, fairness reviews, data residency, and opt-out propagation ship with the layer. Your data office signs off once, not per campaign.

Every point below ships with the layer. Not bolted on later.

Consent-based tracking (cookie + app)

IAB TCF 2.2 vendor consent enforced at the edge — cookie + app tracking disabled for non-consented visitors, with auditable consent-state written to every decision record.

Recommendation-bias review

Weekly fairness audit on recommender outputs across cohorts — over/under-promotion of protected categories flagged, with a review workflow before any policy rollout.

Cross-border data residency

Per-region data pinning for EU, SG, HK, MY, ID, JP, and AU deployments. Model training respects the residency of the underlying training set; no silent cross-border pooling.

Price-personalisation fairness

Price personalisation (where used) audited for protected-class proxies. Dynamic discounting on identifiable cohorts disabled by default; override requires written policy owner.

Explainability per recommendation

Top-signal reason codes surfaced per recommendation — visible to the merchandiser, exportable for compliance review, and translatable to customer-facing language on request.

Opt-out honoured across channels

A single opt-out propagates to web, app, email, signage, and clienteling within minutes. No silent drift between channel-level suppression lists — one customer, one preference.

FRAMEWORKS WE ALIGN TO
Compliance-ready across jurisdictions
GDPRPDPA SGPDPA HKPIPLCCPAISO 27001SOC 2IAB TCF 2.2

Why Axccelerate for personalisation

Not a widget on the PDP.
A layer across the brand.

A widget gives you a carousel. A layer gives you coherent tone across web, app, email, and signage — with holdout-validated lift, consent propagation, and fairness reviews built in.

Feature
Axccelerate
Typical vendor
In-house
Unified layer across web + app + email + signage
Varies
Ensemble ranker + contextual bandit
Varies
Varies
CDP-aware identity stitching
Varies
Varies
In-store signage personalisation
Holdout-validated incremental-lift reporting
Varies
Consent + opt-out propagation across channels
Varies
Varies
Recommender fairness audit included
Category-specific modelling (fashion / beauty / jewellery)
Varies
Varies
Dynamic Yield / Bloomreach / Persado integration
Varies
No vendor lock-in

Pricing

Priced to the surface, not the impression count.

Personalisation deployments are custom — we scope against your surfaces, CDP, and channel mix before quoting.

Launch
Enquirefor pricing
Single-channel start

One surface live — typically PDP + home rails on web, or lifecycle email — with CDP identity, consent, and holdout reporting wired from day one.

1 activation surface
CDP + consent integration
Ranker + bandit modules
Holdout lift reporting
Monthly performance review
Enquire for pricing
Most popular
Scale
Enquirefor pricing
Omnichannel brand

Web + app + email + in-store signage working together — shared feature store, per-surface bandit policies, and unified reporting in InsightAX.

Up to 5 activation surfaces
Shared feature store
Per-surface bandit policies
Category-specific modelling
Bi-weekly model + guardrail review
Enquire for pricing
Fleet
Enquirefor pricing
Enterprise multi-brand

Group-wide deployment across multiple brands and regions — dedicated engineering, private-cloud hosting, per-brand governance, and 24/7 operations coverage.

Unlimited brands + surfaces
Dedicated engineering team
Private-cloud / on-prem option
Per-brand governance
24/7 monitoring + on-call
Talk to us

FAQ

Common questions.

Don't see your question here?

Ask us directly

Glossary

The vocabulary behind every personalised surface.

A quick reference for the terms that show up across merchandising, data, and compliance conversations.

Collab filter
Collaborative filtering

Recommendation approach that relies on behavioural similarity — 'customers like you also bought / viewed X' — without needing deep product-attribute knowledge. Strong for dense catalogues.

Content filter
Content-based filtering

Recommendation approach using product attributes — colour, category, price band, material. Reliable cold-start fallback when behavioural signal on an item is thin.

Contextual bandit
Online learning policy

An algorithm that picks between variants (creative, copy, product) while balancing exploration and exploitation — continuously learning which variant wins in which context.

Cold-start
Sparse-signal scenario

The case where a customer or a product has little history. Content filters and bandit exploration handle cold-start until enough behavioural signal accumulates.

RFV
Recency · Frequency · Value

A cohort segmentation method based on how recently, how often, and how much a customer has spent. Classical in retail, still the backbone of cadence and value-tier routing.

Propensity score
Action-likelihood estimate

A model's estimate of the probability a customer performs an action — buy, click, churn, upgrade. Propensities feed offer targeting, sequencing, and holdout construction.

Cohort
Behavioural / attribute segment

A group of customers sharing a defined behaviour or attribute — 'new SG app users, beauty first-purchase' — used as the unit of bandit arms, content variants, and analytics.

Personalisation surface
Where personalisation renders

A specific placement — PDP, home rail, email hero, signage panel — tuned independently. Surfaces share the same customer profile but carry different content contracts.

Dynamic content
Render-time customisation

Content (image, copy, product module) selected at render or send time based on the requester's profile and context — the mechanism that makes personalisation feel coherent.

Lookalike
Similarity-based audience build

An audience constructed by finding customers behaviourally similar to a seed group. Useful for acquisition, cold-start tuning, and product-discovery expansion.

Segment of one
Single-customer audience

The limit case of personalisation — a cohort size of one, with content tailored to the individual. Reserved for ultra-luxury 1:1 service and high-value clienteling motions.

CDP
Customer Data Platform

The identity, event, and consent layer that unifies customer data across sources. Every surface reads the CDP; every new decision writes back so other surfaces stay in sync.

PII
Personally Identifiable Information

Data that identifies a named individual — name, email, phone, address. Handled with residency, retention, and access controls aligned to GDPR, PDPA, PIPL, and CCPA.

Consent
Permission + purpose

The explicit grant to use customer data for a stated purpose — tracking, marketing, profiling. Recorded per purpose, per jurisdiction, and respected before any decision fires.

Personalisation · lift-measured · consent-first

One customer. Every surface. Coherent tone.

30-minute scoping with a senior engineer and a retail-systems operator. You'll leave with a surface plan, CDP integration sketch, and realistic timeline — not a sales pitch.