AI & Data · Beverage
Cutting cooler repair time by 70% with IoT and machine learning
A world-renowned beverage company managing a vast global network of coolers
The challenge
What the client was trying to solve
Faulty cooler components took too long to repair or replace, and cooler space was not being used to its full potential.
The business problem
- 01
Long repair and replacement cycles for faulty cooler components.
- 02
Cooler space was not optimised, which limited product availability and the customer experience.
- 03
IoT data existed but was not being used for proactive maintenance or streamlined logistics.
Branta's approach
How we worked back from the outcome
Real-time IoT telemetry on Azure feeding a predictive maintenance model, delivered to downstream systems through Databricks and Kubernetes.
Streamed real-time IoT data from the coolers into Azure Cloud to monitor performance and detect anomalies.
Built and deployed a predictive maintenance model in Azure ML Studio to identify faulty parts before they failed.
Used Databricks and Kubernetes to integrate the data and deliver it into downstream systems as seamless workflows.
Turned the data into actionable insights for cooler space utilisation and maintenance scheduling.
Architecture
Problem, thinking, technology, outcome
The system as it runs, from the business problem on the left to the measured result on the right.
- Business problem
Cooler IoT data
Real-time telemetry from the global cooler fleet
- Technology
Azure Cloud
Streaming ingestion, monitoring and anomaly detection
- Technology
Databricks
Data integration and processing
- Branta thinking
Azure ML Studio
Predictive maintenance model identifying faulty parts
- Technology
Kubernetes
Workflows delivered to downstream systems
- Measured outcome
Repairs and space optimised
Repair cycle 10 days to 3 days
Technology
- IoT
- Azure Cloud
- Azure ML Studio
- Databricks
- Kubernetes
- Machine learning
The outcome
Measured, not described
- 70%
- reduction in cooler repair turnaround
- 10 → 3 days
- repair cycle
- 30%
- higher revenue per cooler
- Improved operational efficiency through real-time insight and proactive issue identification.
- Higher cooler utilisation and a better customer experience.
What changed
Maintenance moved from reactive to predictive. Repairs that took ten days now take three, and each cooler earns 30% more.
Related success stories
More problems, solved the same way
AI & Data · EdTech
Converting over 8,000 subscribers with AI-driven prospect modelling
8,000+
unpaid subscribers converted to paying customers
AI & Data · Autonomous vehicles
99.9% accurate training data for safer autonomous driving
99.9%
delivery accuracy
Security · Pharmaceutical manufacturing
Enterprise security operations for a pharmaceutical manufacturer in under 12 weeks
< 12 weeks
to a steady operational state
Have a similar problem? Let's solve it.
Tell us what is not working. We will work backwards from the outcome you need to the technology that gets you there.