Iguazio > Case Studies > Hygiene technologies leader Ecolab brings data science to production with Microsoft Azure and Iguazio

Hygiene technologies leader Ecolab brings data science to production with Microsoft Azure and Iguazio

Customer Company Size

Large Corporate

Region

America

Country

United States

Product

Microsoft Azure
Azure DevOps
Azure Machine Learning
Azure Pipelines
Iguazio

Tech Stack

Python
Git
Kubeflow

Implementation Scale

Enterprise-wide Deployment

Impact Metrics

Cost Savings
Productivity Improvements

Technology Category

Analytics & Modeling - Machine Learning
Platform as a Service (PaaS) - Data Management Platforms

Applicable Industries

Chemicals

Applicable Functions

Discrete Manufacturing
Quality Assurance

Use Cases

Predictive Maintenance
Process Control & Optimization

Services

Data Science Services
System Integration

About The Customer

Ecolab is a major chemicals manufacturer that specializes in water treatment and safety. The company is headquartered in St. Paul, Minnesota and operates in more than 170 countries. Ecolab employs 44,000 people and serves nearly 3 million customer locations in the food, healthcare, hospitality, and industrial markets. The company is driven by a mission to make the world cleaner, safer, and healthier, helping customers succeed while protecting people and vital resources.

The Challenge

Ecolab, a global leader in water, hygiene, and infection prevention solutions, wanted to develop predictive risk models for water systems, industrial machinery, and other applications. The company's machine learning journey began in 2016 with a project to develop bacterial growth risk models using existing sensor data. However, the process of building, deploying, and maintaining machine learning models in production was complex and challenging. The company needed a data science collaboration platform that would bring together its large, geographically dispersed team, while efficiently using cloud computing resources. The deployment of machine learning models at Ecolab followed a 'rewrite-and-deploy' pattern, where model development occurred independent of the application developers. This approach led to deployment timelines exceeding 12 months on average.

The Solution

Ecolab turned to Microsoft Azure and MLOps expert Iguazio to reduce its machine learning development and deployment times, cut costs, and enable its geographically dispersed team to collaborate seamlessly on accelerating the rollout of AI applications. The Iguazio solution, built on an open-source architecture that includes Kubeflow, was readily adopted to extend and simplify the process. Ecolab used Iguazio in combination with Git and Azure DevOps to develop the feature engineering pipelines and machine learning applications. The solution also brings direct visibility into the code that is running during production. The deployment of the Iguazio platform coincided with the eruption of the COVID-19 health crisis, fueling a dramatic increase in demand to incorporate data science models into Ecolab’s broader digital offerings.

Operational Impact

With the adoption of the Iguazio platform, deployment times for highly secure, scalable compute resources decreased from days to minutes.
Ecolab was able to reduce costs by running in a shared compute environment.
Model development time dropped dramatically. Prior to implementing this solution, model deployment times exceeded 12 months. Thanks to Iguazio and Microsoft Azure, by 2020, initial deployment timelines had been reduced to between 30 and 90 days.
The solution brings direct visibility into the code that is running during production.

Quantitative Benefit

Deployment times for compute resources decreased from days to minutes.
Model development time reduced from over 12 months to between 30 and 90 days.
By the end of 2020, Ecolab had more than 40 users—more than double what it had anticipated. And three to four times more models running than originally planned.