Sift Case Studies How Curve slashed chargebacks and streamlined fraud review

Edit This Case Study Record

	How Curve slashed chargebacks and streamlined fraud review Sift

How Curve slashed chargebacks and streamlined fraud review

Sift

Technology Category	Analytics & Modeling - Machine Learning
Applicable Industries	Finance & Insurance
Applicable Functions	Sales & Marketing
Use Cases	Fraud Detection
Services	Data Science Services
Challenge	Curve, a company that offers a smart bank card that combines all your cards in one, was facing a growing threat of fraud due to its rapidly expanding customer base. The ability to quickly add new cards with the Curve app and then use them within moments was of particular interest to malicious users who tried to circumvent Curve’s many layers of account authentication. This resulted in expensive manual resources for fraud reviews and chargeback management. As the business was growing at a fast pace, Curve needed a solution to preemptively knock out the growing threat of fraud. Read More
About Customer	Curve is a company that offers a smart bank card that combines all your cards in one. The Curve app, paired with the smart bank card, works like a normal bank card anywhere in the world that accepts MasterCard. Users don’t need to open a new bank account and don’t need to wait for weeks — after a few taps and a new Curve card in the post, they’re ready to go. With Curve, customers benefit from simpler spending across all their cards, saving money on currency exchange, a smarter and faster way to manage expenses, instant cashback rewards at over 50 leading UK retailers, plus a host of additional security features. Curve users have so far spent £50 million in over 100 currencies, worldwide. Read More
Solution	Curve decided to implement a machine learning solution to avoid having to spend precious resources on building an in-house rules engine from scratch. After reviewing several vendor options, Curve decided to go with Sift and quickly integrated the solution. Curve first implemented the basic Sift Score API, and soon began using Sift’s findings to assess real-time transactional data. Within weeks of training the models and learning how to use Sift effectively, Curve began to trust the accuracy of Sift Scores. Now, Curve takes a layered approach to fraud management, relying on an in-house rules engine to weed out the hard-and-fast business blacklist while utilizing Sift to spot the trickier fraudsters, ideally before they even get a Curve card. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Finance & Insurance

Applicable Functions

Sales & Marketing

Use Cases

Fraud Detection

Services

Data Science Services

Challenge

Curve, a company that offers a smart bank card that combines all your cards in one, was facing a growing threat of fraud due to its rapidly expanding customer base. The ability to quickly add new cards with the Curve app and then use them within moments was of particular interest to malicious users who tried to circumvent Curve’s many layers of account authentication. This resulted in expensive manual resources for fraud reviews and chargeback management. As the business was growing at a fast pace, Curve needed a solution to preemptively knock out the growing threat of fraud.

About Customer

Curve is a company that offers a smart bank card that combines all your cards in one. The Curve app, paired with the smart bank card, works like a normal bank card anywhere in the world that accepts MasterCard. Users don’t need to open a new bank account and don’t need to wait for weeks — after a few taps and a new Curve card in the post, they’re ready to go. With Curve, customers benefit from simpler spending across all their cards, saving money on currency exchange, a smarter and faster way to manage expenses, instant cashback rewards at over 50 leading UK retailers, plus a host of additional security features. Curve users have so far spent £50 million in over 100 currencies, worldwide.

Solution

Curve decided to implement a machine learning solution to avoid having to spend precious resources on building an in-house rules engine from scratch. After reviewing several vendor options, Curve decided to go with Sift and quickly integrated the solution. Curve first implemented the basic Sift Score API, and soon began using Sift’s findings to assess real-time transactional data. Within weeks of training the models and learning how to use Sift effectively, Curve began to trust the accuracy of Sift Scores. Now, Curve takes a layered approach to fraud management, relying on an in-house rules engine to weed out the hard-and-fast business blacklist while utilizing Sift to spot the trickier fraudsters, ideally before they even get a Curve card.

Impact #1	Streamlined fraud workflows with a single platform for automation, review, and investigation.
Impact #2	Fraud management no longer requires a whole team.
Impact #3	More time and better data for in-depth investigations on the fraud cases they encounter.

Impact #1

Streamlined fraud workflows with a single platform for automation, review, and investigation.

Impact #2

Fraud management no longer requires a whole team.

Impact #3

More time and better data for in-depth investigations on the fraud cases they encounter.

Benefit #1	80% Drop in chargebacks
Benefit #2	Only had to add one full-time fraud resource despite business booming

Benefit #1

80% Drop in chargebacks

Benefit #2

Only had to add one full-time fraud resource despite business booming

Download PDF Version

Overview

How Curve slashed chargebacks and streamlined fraud review

Operational Impact

Quantitative Benefit