Iguazio Case Studies Payoneer Case Study

Edit This Case Study Record

	Payoneer Case Study Iguazio

Payoneer Case Study

Iguazio

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Predictive Analytics Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries	Finance & Insurance Retail
Applicable Functions	Business Operation Sales & Marketing
Use Cases	Fraud Detection Predictive Quality Analytics Real-Time Location System (RTLS)
Services	Data Science Services System Integration
Challenge	Payoneer, a digital payment platform, needed a way to serve its AI/ML fraud predictive/preventative models against fresh, real-time data to provide their customers with a safer payment experience. The company was using a retroactive approach that detected fraud attempts after the fact, which meant customers could only block users after a (possibly successful) fraud attempt. This approach had several limitations including the inability to track fraud attempts across complex networks, lack of advanced analytics and log correlation to identify anomalies, and a negative impact on customer experience and satisfaction. Payoneer needed a solution that leveraged sophisticated algorithms to track multiple parameters and detect fraud within complex networks. While Payoneer had built sophisticated machine learning models, these only worked offline and could not be used against real-time threats. Read More
About Customer	Payoneer’s digital platform streamlines global commerce for millions of small businesses, marketplaces and enterprises from 200 countries and territories. Their innovative end-to-end platform enables businesses to expand their products and services and reach clients worldwide. As such, millions of individuals and businesses around the world rely on Payoneer to make and receive cross-border payments. In the face of an increasingly dangerous cybersecurity landscape and the pervasiveness of fraud and money laundering activities, Payoneer came up with an innovative initiative to keep their customer’s money safe. Read More
Solution	Payoneer chose Iguazio to bring its most intelligent data science strategies to life. The data science platform allowed Payoneer to deploy and run its predictive machine learning models in real-time. This resulted in a scalable and reliable fraud prediction and prevention tool that could analyze fresh data in real-time and adapt to new threats, thus making fraud attacks almost impossible on Payoneer. Payoneer deployed Iguazio to power its predictive ML models and serve them in real-time against fresh data. This facilitated continuous monitoring of suspicious patterns and prevention of fraud with minimum false positives. The production pipeline is based on Python code that is running via Nuclio functions and Spark framework. This approach doesn’t require conversion of code from Python to Java or others. Python is used all the way up to live deployment. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Predictive Analytics

Application Infrastructure & Middleware - Data Exchange & Integration

Applicable Industries

Finance & Insurance

Retail

Applicable Functions

Business Operation

Sales & Marketing

Use Cases

Fraud Detection

Predictive Quality Analytics

Real-Time Location System (RTLS)

Services

Data Science Services

System Integration

Challenge

Payoneer, a digital payment platform, needed a way to serve its AI/ML fraud predictive/preventative models against fresh, real-time data to provide their customers with a safer payment experience. The company was using a retroactive approach that detected fraud attempts after the fact, which meant customers could only block users after a (possibly successful) fraud attempt. This approach had several limitations including the inability to track fraud attempts across complex networks, lack of advanced analytics and log correlation to identify anomalies, and a negative impact on customer experience and satisfaction. Payoneer needed a solution that leveraged sophisticated algorithms to track multiple parameters and detect fraud within complex networks. While Payoneer had built sophisticated machine learning models, these only worked offline and could not be used against real-time threats.

About Customer

Payoneer’s digital platform streamlines global commerce for millions of small businesses, marketplaces and enterprises from 200 countries and territories. Their innovative end-to-end platform enables businesses to expand their products and services and reach clients worldwide. As such, millions of individuals and businesses around the world rely on Payoneer to make and receive cross-border payments. In the face of an increasingly dangerous cybersecurity landscape and the pervasiveness of fraud and money laundering activities, Payoneer came up with an innovative initiative to keep their customer’s money safe.

Solution

Payoneer chose Iguazio to bring its most intelligent data science strategies to life. The data science platform allowed Payoneer to deploy and run its predictive machine learning models in real-time. This resulted in a scalable and reliable fraud prediction and prevention tool that could analyze fresh data in real-time and adapt to new threats, thus making fraud attacks almost impossible on Payoneer. Payoneer deployed Iguazio to power its predictive ML models and serve them in real-time against fresh data. This facilitated continuous monitoring of suspicious patterns and prevention of fraud with minimum false positives. The production pipeline is based on Python code that is running via Nuclio functions and Spark framework. This approach doesn’t require conversion of code from Python to Java or others. Python is used all the way up to live deployment.

Impact #1	Seamless transition from reactive to proactive fraud prediction and prevention using real-time ML
Impact #2	Understanding illicit patterns of behavior in real-time based on 90 different parameters
Impact #3	Detection and prevention of money laundering before it occurs

Impact #1

Seamless transition from reactive to proactive fraud prediction and prevention using real-time ML

Impact #2

Understanding illicit patterns of behavior in real-time based on 90 different parameters

Impact #3

Detection and prevention of money laundering before it occurs

Benefit #1	ROI reached in 4 months
Benefit #2	A scalable, and reliable fraud prevention system that adapts to new threats in real-time
Benefit #3	Safer payment experience for 4 million+ customers worldwide

Benefit #1

ROI reached in 4 months

Benefit #2

A scalable, and reliable fraud prevention system that adapts to new threats in real-time

Benefit #3

Safer payment experience for 4 million+ customers worldwide

Download PDF Version

Overview

Payoneer Case Study

Operational Impact

Quantitative Benefit