Smart Retail Experience — Ayurtam
Visual: shelf-level analytics, in-store kiosk, and customer journey heatmaps.
Client Overview
Ayurtam is a fast-growing herbal wellness retail chain that blends traditional remedies and modern formulations. With a growing physical store footprint across tier-2 and tier-3 cities, Ayurtam sought to modernize in-store experiences and use data to improve merchandising and personalized customer engagement.
Challenge
Ayurtam lacked granular visibility into shelf-level product interactions, in-store customer journeys, and local demand patterns. Marketing had limited tools to personalize offers in real time, and stockouts in fast-moving seasonal SKUs were frequent.
Goals: improve shelf analytics, personalize in-store recommendations, reduce stockouts, and raise conversion rates.
Solution — In-Store IoT & Personalization Stack
We designed a lightweight IoT and edge-analytics solution for Ayurtam that combined shelf sensors, footfall beacons, smart kiosk recommendations, and a cloud-based personalization engine to deliver contextual offers and actionable insights to store managers.
Core components
Approach
- Pilot in 8 stores to validate sensor placement and map common customer paths.
- Collect 6 weeks of event data and train simple uplift models for recommendation triggers.
- Roll out personalized kiosk suggestions and low-friction SMS coupons to loyalty members.
- Integrate replenishment alerts with ERP and local store ordering workflows.
Technology stack
Implementation — Phases
Phase 1 — Pilot & Sensor Validation (Weeks 1–6)
Sensor placement, footfall mapping, and initial event stream validation to ensure signal quality in different store layouts.
Phase 2 — Personalization Model & Kiosk UX (Weeks 7–14)
Developed simple intent classifiers and a lightweight kiosk UI for in-store recommendations; integrated with loyalty IDs for contextual messaging.
Phase 3 — Rollout & Inventory Integration (Weeks 15–22)
Phased expansion to 60 stores, integration with ERP for replenishment, and staff training for using dashboards.
Phase 4 — Optimize & Expand (Weeks 23–30)
Model tuning, seasonal SKU experiments, and expanded messaging strategies for local festivals.
Impact & Results
18%
Increase in conversion at kiosk-influenced zones
28%
Reduction in stockouts for targeted SKUs
12%
Lift in average basket value (pilot stores)
3 months
Time to measurable uplift after pilot
Qualitative outcomes
- Localized offers driven by in-store signals resonated better than broad discounts.
- Store managers used heatmaps to improve product placement and planogram decisions.
- Edge aggregation reduced connectivity costs while preserving near real-time insights.
Client Testimonial
Key Highlights & Learnings
- Start with high-traffic zones to show quick wins for in-store IoT pilots.
- Edge preprocessing is cost-effective for multi-store rollouts with limited bandwidth.
- Localized recommendations—paired with loyalty—improve conversion without heavy discounting.