Software AG > Case Studies > Squashing Financial Fraud Faster with the Power of Predictive Analytics

Squashing Financial Fraud Faster with the Power of Predictive Analytics

Software AG Logo
Customer Company Size
Large Corporate
Product
  • Zementis Predictive Analytics
Tech Stack
  • Predictive Model Markup Language (PMML)
  • Machine Learning
  • Artificial Intelligence
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Cost Savings
  • Productivity Improvements
  • Customer Satisfaction
Technology Category
  • Analytics & Modeling - Predictive Analytics
Applicable Industries
  • Finance & Insurance
Applicable Functions
  • Business Operation
Use Cases
  • Fraud Detection
  • Predictive Quality Analytics
Services
  • Data Science Services
About The Customer
The customer is a leading global financial services company providing data and analytics solutions to businesses, consumers, and governments. Its solutions range from all aspects of credit modeling and scoring, to fraud detection and prevention, to identity management and verification services. The company offers customers a diverse portfolio of services and management options. With millions of customer accounts, a growing and large service portfolio, new product launches, and geographically dispersed operations, the company was facing challenges in managing the complexity of its operations. The company's annual revenue exceeds $3 billion a year with an operating income of more than $2 billion.
The Challenge
The customer, a leading global financial services company, was facing challenges due to its diverse portfolio of services and management options. The complexity of analytic models increased as the company grew, and the internal data science and IT teams were reaching their capacity. This increased the underlying risk of the company’s business model and threatened to remove a competitive advantage. The company was using a dedicated team of data scientists creating hand-coded fraud models. However, with millions of customer accounts, a large service portfolio, new product launches, and geographically dispersed operations, manual coding became a major liability. The process of converting algorithmic fraud models to “production ready” dramatically slowed the process of integrating them into the operational business processes.
The Solution
The company implemented Zementis Predictive Analytics, part of the Software AG Digital Business Platform. This solution combined machine learning, artificial intelligence technologies, and next-generation Internet of Things-type streaming data analytics to provide automated predictive models for better risk scoring and fraud detection. The initial implementation focused on detecting anomalies in financial transfers, with the goal of identifying money laundering. With strong results, the company adopted Zementis Predictive Analytics more broadly in its cross-channel fraud detection efforts. The solution provided its functionality as a plug-in tool for other leading analytics and data warehouse platforms, using the Predictive Model Markup Language (PMML) industry standard.
Operational Impact
  • The company was able to automate the process of operationalizing fraud management models without the need to manually write custom code.
  • The company's data scientists were able to focus on modeling fraud rather than fixing mistakes.
  • The company was able to use advanced predictive models to detect and analyze customer behavior, market dynamics, security risks, and other variables necessary for quick and precise fraud detection.
  • The company was able to run multiple models simultaneously to analyze complex, multi-factor situations.
Quantitative Benefit
  • Analytics-based decisions that previously required months of preliminary analysis now required only days, sometimes even hours, enabling near real-time decision making.

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.