Download PDF
Seldon > Case Studies > Noitso accelerates model deployment from days to hours
Seldon Logo

Noitso accelerates model deployment from days to hours

Technology Category
  • Analytics & Modeling - Machine Learning
  • Platform as a Service (PaaS) - Application Development Platforms
Applicable Industries
  • Finance & Insurance
Applicable Functions
  • Business Operation
Use Cases
  • Predictive Quality Analytics
  • Predictive Replenishment
Services
  • Data Science Services
  • Software Design & Engineering Services
The Challenge
Noitso, a company based in Copenhagen, Denmark, specializes in data science, data collection, and predictive analysis. They provide their customers with credit ratings, scorecards, and risk profiles using data science and AI. However, they faced challenges in deploying their models. The models took a long time to get to production and lacked explainability and monitoring. They were unable to determine when models needed to be retrained, and had to do it after a fixed period of time rather than when necessary. This approach was the only way to maintain accurate predictions and prevent issues such as data drift.
About The Customer
Noitso is a company based in Copenhagen, Denmark, founded in 2007. They specialize in data science, data collection, and predictive analysis. Their mission is to use data science and AI to provide their customers with credit ratings, scorecards, and risk profiles. Their customers have use cases ranging from inferring budgets and credit rating, to enterprise data management and scorecards with machine learning used to capture high-risk events. They aim to make vital business decisions accurately using their dynamic solutions to work with big data and AI.
The Solution
Noitso introduced Seldon Deploy to their MLOps stack to improve their model deployment process. Seldon Deploy is a machine learning deployment platform that allows data scientists to deploy, scale, and monitor models in production. With Seldon Deploy, Noitso was able to deploy their machine learning models faster and more accurately. The platform also provided them with the necessary tools to manage code and collaborate with data-savvy colleagues. As a result, Noitso was able to impress their existing customers with faster and more accurate AI, and they plan to roll out this new approach to more customers soon.
Operational Impact
  • Models are now deployed faster, reducing the deployment time from days to hours.
  • Models are no longer a black box to users, improving transparency and trust.
  • The new system allows for better monitoring and explainability of models.
Quantitative Benefit
  • Reduced model deployment time from days to hours.
  • Improved model accuracy and reliability in production.
  • Increased customer satisfaction due to faster and more accurate AI.

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.