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

Edit This Case Study Record

	Independent Model Validation through DataRobot’s AI Services DataRobot

Independent Model Validation through DataRobot’s AI Services

DataRobot

Technology Category	Analytics & Modeling - Predictive Analytics Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries	Finance & Insurance
Applicable Functions	Business Operation
Use Cases	Fraud Detection Predictive Maintenance
Services	Data Science Services
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. Read More
About 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. Read More
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. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Application Infrastructure & Middleware - Data Exchange & Integration

Applicable Industries

Finance & Insurance

Applicable Functions

Business Operation

Use Cases

Fraud Detection

Predictive Maintenance

Services

Data Science Services

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.

About 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.

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.

Impact #1	The fintech company was able to align their business process to regulatory compliance requirements.
Impact #2	They were able to validate their models independently, meeting the rigorous regulatory expectations required by their partner bank.
Impact #3	The company plans to partner with DataRobot’s AI Services on a yearly basis for their model validation needs, ensuring ongoing compliance.

Impact #1

The fintech company was able to align their business process to regulatory compliance requirements.

Impact #2

They were able to validate their models independently, meeting the rigorous regulatory expectations required by their partner bank.

Impact #3

The company plans to partner with DataRobot’s AI Services on a yearly basis for their model validation needs, ensuring ongoing compliance.

Benefit #1	Increased confidence in meeting regulatory expectations.
Benefit #2	Improved model accuracy and diversification.
Benefit #3	Faster deployment speed of machine learning models.

Benefit #1

Increased confidence in meeting regulatory expectations.

Benefit #2

Improved model accuracy and diversification.

Benefit #3

Faster deployment speed of machine learning models.

Download PDF Version

Overview

Independent Model Validation through DataRobot’s AI Services

Operational Impact

Quantitative Benefit