Omnichannel Customer Experience at a UK Retailer — Unified View Across 480 Stores, App and Web
Customer 360 + Multi-Channel Agent + Churn Predictor unifying the customer experience across store, app and web for a UK national retailer.
The challenge
The retailer — a UK national retailer with 480 stores plus a mature mobile app and web presence — was operating with a structurally fragmented customer view across its channels. Customers who shopped both in-store and online appeared as different customers in the underlying systems: the in-store loyalty data sat in one system, the mobile-app behaviour data in another, the web-purchase data in a third, the customer-service-interaction data in a fourth. The result was that the retailer's marketing, customer-service and store-operations teams each operated on a partial view of the customer, with the cross-channel customer-experience implications visible to nobody.
The customer-experience consequences were measurable. The retailer's customer-experience research consistently identified cross-channel friction as the leading dissatisfaction driver — customers who started a transaction online and continued in-store, or vice versa, experienced the channel-transition as fragmented and inconsistent. The retailer's marketing function was running siloed channel campaigns rather than orchestrated customer-journeys, with the resulting marketing-spend inefficiency apparent in the per-incremental-sale measurement.
The constraints were structural. The retailer's existing channel systems (the in-store POS, the mobile-app platform, the web-commerce platform, the customer-service CRM) could not be replaced wholesale. GDPR compliance applied to all customer-data handling. The retailer's customer base of approximately 22 million UK customers represented a substantial PII exposure that required appropriate technical and organisational measures.
The approach
MindMap deployed an omnichannel customer-experience platform composed of Customer 360 (C3) as the unified-customer-profile layer, Multi-Channel Agent (Mh) for the cross-channel experience unification, Churn Predictor (Ch) for the customer-value modelling, and Churn Predictor (Ch) for the customer-lifetime-value layer.
Phase one was the customer-identity-resolution build. The challenge was to consolidate the multiple customer-identity representations across the channels into a unified customer-identity-graph. The graph uses deterministic matching where available (the customer's loyalty-card number across in-store and mobile-app), probabilistic matching where deterministic identifiers are not available (the customer's email, phone, address, payment-method signature combinations), and customer-confirmed merging where the probabilistic matching produces high-likelihood candidates.
Phase two was the unified-customer-profile build. For each unified customer-identity, the platform builds a comprehensive customer profile spanning all the channel sources — purchase history across in-store and online, mobile-app behaviour, web-browsing behaviour (with appropriate consent), customer-service-interaction history, loyalty-programme status, marketing-engagement history. The profile is refreshed near-real-time as new channel-events arrive.
Phase three was the cross-channel-experience build. For customers whose journey spans channels, the platform enables the cross-channel experience continuity — a customer browsing on the app sees the products they were looking at in-store, a customer entering a store sees the items they had added to their online basket, a customer-service-interaction has full visibility of the customer's cross-channel context.
Phase four was the customer-value-modelling build. Churn Predictor models the per-customer churn risk across the omnichannel relationship (the customer doesn't churn from a single channel; they reduce or stop their relationship with the retailer overall). LTV Calculator models the per-customer lifetime value to support marketing-spend prioritisation.
The pre-built building blocks
Rather than commission a ground-up build, the engagement leaned on MindMap's pre-built accelerator library — production-tested components that compress what would otherwise be a six-to-nine-month build into weeks.
Customer 360
Unified customer-profile layer with cross-channel identity resolution
Multi-Channel Agent
Cross-channel experience-continuity layer
Churn Predictor
Omnichannel customer-churn modelling
Churn Predictor
Per-customer lifetime-value modelling
The architecture
The platform runs on the retailer's Azure tenant in the UK region with full GDPR compliance and the retailer's data-protection-officer's required technical and organisational measures.
The customer-identity-resolution layer uses a combination of deterministic-matching, probabilistic-matching and customer-confirmed-merging. The identity-graph is held in Neo4j with a custom schema modelling the customer's identity representations across channels and the relationships between them.
Customer 360's unified-customer-profile layer uses a streaming-ingestion architecture on Kafka, with the channel-event streams from the in-store POS, mobile-app, web-commerce and customer-service CRM all flowing into the profile-update pipeline. The profile-data is held in a combination of structured (PostgreSQL) and semi-structured (document-store) storage with appropriate access-control layers.
Multi-Channel Agent provides the cross-channel-experience-continuity layer. The customer's cross-channel context (items viewed, items in basket, recent purchases, service-interaction history) is available to each channel through the appropriate channel-integration API. The integration with the channel systems is bi-directional — each channel both feeds the platform and consumes the cross-channel context.
Churn Predictor and LTV Calculator provide the customer-value-modelling layer. The models use the full unified-customer-profile features and produce per-customer churn-risk and lifetime-value scores that flow into the retailer's marketing-and-CRM workflow.
GDPR compliance is enforced by construction: customer-consent management is integrated with every data-use decision, customer-rights requests (access, deletion, correction) are handled through a standard workflow, the retailer's data-protection-officer has direct query and audit access to the full data-processing chain.
The numbers behind the story
Approximately 22 million unified customer profiles are now live on the platform, representing approximately 95% of the retailer's identifiable customer base across the channels. The 5% gap is concentrated in the customer-segments where the identity-resolution data is structurally limited (e.g. anonymous web-browsers who have not yet provided identity signals).
Cross-channel customer value (the per-customer total annual spend across the retailer's channels) has risen approximately 18% for the customers who have engaged with the cross-channel-experience features. The lift is driven by the experience-continuity improvements (customers find their cross-channel journey easier and complete more of it) and by the more-targeted marketing (the platform-informed marketing targeting drives incremental cross-channel engagement).
Marketing-spend efficiency has risen materially on the platform-informed campaigns. The combination of better customer-targeting (the unified profile supports more precise audience definition), better channel-orchestration (the campaigns can engage the customer across the right combination of channels for the customer's pattern), and the value-based prioritisation (the LTV modelling directs spend to the customers where the return is highest) has produced a substantial per-incremental-sales-driver improvement.
Customer-service productivity has improved as well. The customer-service-interaction's full cross-channel context — including the customer's recent in-store visit, recent app-engagement, recent web-purchase — is available to the customer-service agent at the start of the interaction, eliminating much of the previous context-gathering work and producing more-resolution-on-first-contact outcomes.
GDPR-compliance posture has been maintained throughout the rollout. The retailer's data-protection officer has confirmed the platform's compliance with the relevant requirements, and the retailer's annual ICO-audit-readiness assessment has been positively impacted by the platform's structured data-processing-and-consent management.
“Our customers were experiencing the channel transitions as fragmented and inconsistent because our underlying systems treated them as different customers. MindMap delivered the unified customer view across our store, app and web channels with the cross-channel experience-continuity that has produced an eighteen per cent cross-channel customer-value uplift. The platform has changed how we think about the customer relationship.”— Chief Customer Officer· UK Omnichannel Retailer
Why MindMap was chosen
The retailer had evaluated several customer-data-platform vendors. The leading vendors were strong on the customer-profile-unification capability but had limited cross-channel-experience-continuity capability and limited UK-GDPR-specific compliance depth.
MindMap's accelerator-composition approach — bringing Customer 360, Multi-Channel Agent, Churn Predictor and LTV Calculator together with the cross-channel-experience-continuity layer and the GDPR-by-design compliance — was the structural differentiator.
Our embedded UK retail expertise on the delivery team (two former CMOs from peer UK national retailers and a former retail-CRM lead) was the third factor. The retailer's CCO felt that the team understood the operational reality of UK omnichannel retail.
Related deployments
Pan-African FMCG Forecasting
Demand Forecaster delivered SKU-market forecasts across 18 African countries — cutting stockouts 22% while reducing overall inventory 14%.
Grocery Planogram Optimisation
An ML-driven planogram-optimisation platform delivered a 6.4% like-for-like sales lift across 1,200 stores — through per-store assortment and shelf-position tuning.
Global CPG Supplier Intelligence
Supplier Benchmarker + Anomaly Detector delivered continuous risk visibility across 12,000 Tier-1 suppliers — early warning on 84% of subsequent disruptions.
Want an outcome like this?
Start with a 2-week AI Readiness Sprint. We deliver a prioritised use-case backlog and business case grounded in what's actually buildable with our accelerator library.