Case-Study-Actowiz-Solutions-–-ML-Driven-Cart-Abandonment-Triggers-from-SKU-Trends-in-Zapp-UK

Introduction

Zapp, one of the fastest-growing Q-commerce platforms in the UK, delivers essentials within minutes. But with fierce competition from Getir, GoPuff, and Deliveroo Express, abandoned carts represent lost revenue—and missed insights.

Actowiz Solutions helped a major UK-based consumer goods brand integrate machine learning models and real-time scraping to detect and analyze SKU-level cart abandonment triggers on Zapp. The result: smarter campaign targeting, better pricing, and reduced drop-offs.

Client Objectives

Identify what SKUs are most frequently abandoned before checkout on Zapp
Understand behavioral triggers behind drop-offs (price, timing, stock)
Predict cart abandonment risk based on product type and time-of-day
Correlate discount patterns and abandonment likelihood
Generate alerts for high-risk product combinations in real time

Challenges Faced

🛒 Zapp doesn’t offer cart data publicly—behavior needed to be reverse-engineered
📉 SKU trends changed hourly with dynamic pricing and availability
⚡ Cart abandonment could spike due to delays, pricing, or stockouts
📦 Identifying multi-SKU interactions (e.g., bundles abandoned) required clustering
🧠 Client lacked predictive modeling for drop-off scenarios

Actowiz’s AI/ML & Data Scraping Strategy

🔍 1. Scraping User-Facing Signals on Zapp

Actowiz deployed a Zapp scraper capturing:

SKU availability, price, and discounts
“Low stock” tags, delivery ETA, and cart limits
Add-to-cart button status & changes
Repeat pattern tracking (e.g., items added repeatedly but never purchased)

Data was extracted across London, Manchester, Birmingham zones every 15–30 minutes.

📊 2. Data Points Extracted

Timestamp	City	SKU Name	Price	Stock Status	Discount	Delivery ETA	Add-to-Cart Status
2025-06-15 18:00	London	Alpro Almond 1L	£2.10	Low Stock	10%	22 mins	Enabled
2025-06-15 18:00	London	Cadbury Buttons	£1.80	In Stock	0%	16 mins	Enabled
2025-06-15 18:00	London	Dettol Wipes 20ct	£2.50	In Stock	5%	26 mins	Enabled

🧠 3. Machine Learning Models Deployed

Logistic Regression – Classified SKUs by likelihood of abandonment
XGBoost Classifier – Scored risk levels based on discount, stock, and timing
K-Means Clustering – Grouped abandoned SKUs by behavioral signals
Sequence Pattern Mining – Detected repeat abandonment patterns by users

Top Abandonment Triggers Identified

🧾 Key Findings:

Abandonment Trigger	Impact Detected
Delivery ETA > 25 mins	+38% likelihood of cart drop-off
Discount < 5%	2.3x more likely to be abandoned
Low Stock Tag	Increased hesitation on checkout
Multi-SKU Cart (3+ items)	Drop-off spike due to perceived complexity
Repeatedly Viewed SKU	Abandoned unless offered discount in 24 hrs

Cart Abandonment Heatmap by Time of Day (London)

Time Slot	Avg Cart Abandonment Rate
8 AM – 11 AM	18%
12 PM – 3 PM	26%
4 PM – 7 PM	32%
8 PM – 11 PM	21%

🔍 Insight: Evening hours saw highest drop-offs—often due to peak ETA delays or unavailable fast-moving SKUs.

Real-World Example:

SKU: Magnum Classic Ice Cream

📍 London SW6
Regular Price: £3.50
Offered 5% discount → Drop rate: 29%
Offered 15% discount → Drop rate: 9%

Actowiz flagged this behavior for the client, prompting strategic discounting only after first drop-off detection.

Actowiz Dashboard Highlights

Feature	Description
SKU Drop-Off Risk Scoring	Visualize real-time cart abandonment likelihood per product
Time-Based Abandonment Patterns	Analyze hourly/day-wise cart abandonment trends
Trigger Alert System	Push alerts for high-risk SKU combos
Multi-SKU Cart Drop Analysis	Track how cart complexity affects purchase behavior
Promo Recommendation Engine	Suggest optimal discount % based on historic abandonment elasticity

Geographic Coverage

Monitored regions across Zapp in the UK:

London (SW6, NW1, E14, EC1, SE10)
Manchester (M1–M16 zones)
Birmingham (B1–B33 regions)
Leeds, Bristol, Liverpool – added in Phase 2

Business Impact Delivered

📈 Results after 60 Days of Implementation:

KPI	Before Actowiz	After Actowiz
Average Cart Abandonment Rate	36%	19%
Time to Detect Drop-Off Pattern	Manual (24h+)	Real-Time
Discount ROI (after AI-driven targeting)	-	+31% uplift
SKUs Recovered via Promo Alert	-	800+ SKUs
Multi-SKU Cart Conversions	41%	63%

Client Testimonial

“We never had real visibility into Zapp cart behavior. Actowiz gave us the triggers, patterns, and recommendations to turn drop-offs into conversions.”

– E-Commerce Lead, UK FMCG Brand Partnering with Zapp

Next Steps

Integrate behavioral email/SMS triggers tied to SKU abandonment
Expand insights to Amazon Fresh, GoPuff, and Deliveroo UK
Add price elasticity models by category
Build competitive benchmarking layer (e.g., Zapp vs Getir)

Conclusion

In a Q-commerce ecosystem where consumers make split-second decisions, understanding why carts are abandoned can unlock substantial revenue.

Actowiz Solutions transformed SKU-level scraping and ML modeling into a high-ROI abandonment prediction tool—helping Zapp’s brand partners reclaim lost sales across the UK.

In a world where milliseconds matter, Actowiz lets brands act at the right moment.

Hear It Directly from Our Clients

Watch how businesses like yours are using Actowiz data to drive growth.

▶

1 min

★★★★★

"Actowiz Solutions offered exceptional support with transparency and guidance throughout. Anna and Saga made the process easy for a non-technical user like me. Great service, fair pricing!"

Thomas Galido

Co-Founder / Head of Product at Upright Data Inc.

▶

2 min

★★★★★

"Actowiz delivered impeccable results for our company. Their team ensured data accuracy and on-time delivery. The competitive intelligence completely transformed our pricing strategy."

Iulen Ibanez

CEO / Datacy.es

▶

1:30

★★★★★

"What impressed me most was the speed — we went from requirement to production data in under 48 hours. The API integration was seamless and the support team is always responsive."

Febbin Chacko

-Fin, Small Business Owner