DataRobot > Case Studies > Independent Model Validation through DataRobot’s AI Services

Independent Model Validation through DataRobot’s AI Services

DataRobot Logo
Customer Company Size
Large Corporate
Region
  • America
Country
  • United States
Product
  • DataRobot’s Enterprise AI platform
  • DataRobot’s AI Services
Tech Stack
  • Machine Learning
  • Predictive Models
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Productivity Improvements
  • Digital Expertise
Technology Category
  • Analytics & Modeling - Predictive Analytics
  • Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries
  • Finance & Insurance
Applicable Functions
  • Business Operation
Use Cases
  • Predictive Maintenance
  • Fraud Detection
Services
  • Data Science Services
About The Customer
The customer is a leading fintech company based in the US. They help customers across all industries obtain the capital and payment plans they need to purchase goods and services. They also assist merchants and service suppliers in increasing sales through credit programs. The company uses machine learning models for decision-making, which is critical in the highly regulated financial industry. They have several models built on DataRobot’s platform and deployed into production, including an internal credit score model, a fraud score model, and a dealer score model.
The Challenge
The fintech company, based in the US, was facing challenges in aligning their business process to regulatory compliance requirements. They were using machine learning models for decision-making, which increased the stakes due to the highly regulated nature of the industry. The company was already using DataRobot’s Enterprise AI platform to improve their model-building, but they needed to accelerate the alignment of their business process to model risk management regulation. They had several models built on DataRobot’s platform and deployed into production, including an internal credit score model, a fraud score model, and a dealer score model. However, they needed an independent model validation after partnering with a bank, which was a critical component of their partnership.
The Solution
The fintech company engaged with DataRobot’s AI Services to independently validate their models. The AI Services team at DataRobot, which operates autonomously from the rest of the company, worked independently through the five main stages of the validation engagement: project planning, documentation and methodology review, model performance, testing and analysis, and preparation of the final model validation report and workpapers. The team delivered the independent validation that the fintech needed, complete with a Model Validation Report that describes how a model works in detail, and what was done to effectively challenge that model’s development during the validation process. The company plans to partner with DataRobot’s AI Services on a yearly basis for their model validation needs.
Operational Impact
  • The fintech company was able to align their business process to regulatory compliance requirements.
  • They were able to validate their models independently, meeting the rigorous regulatory expectations required by their partner bank.
  • The company plans to partner with DataRobot’s AI Services on a yearly basis for their model validation needs, ensuring ongoing compliance.
Quantitative Benefit
  • Increased confidence in meeting regulatory expectations.
  • Improved model accuracy and diversification.
  • Faster deployment speed of machine learning models.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

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.