Aite Group, a global research and advisory firm, have just published a report on Fraud and AML Machine Learning Platform Vendors which looked at how these platforms are being used in the fight against financial crime. These systems represent the next generation of detection and mitigation, and they provide a way for businesses to harness one of their greatest assets—their customer data—and apply custom analytics that can evolve with the rapid pace of financial crime.
Using the Aite Impact Matrix (AIM), a proprietary Aite Group vendor assessment framework, this Impact Report evaluates the overall competitive position of 14 vendors, focusing on vendor stability, client strength, product features, and client services.
Developing machine learning models
The primary goal of firms investing in machine learning platforms is to improve their ability to detect fraud or money laundering while reducing false positives and to have analytics that can nimbly and responsively evolve with emerging attack vectors. To reach this goal, a good deal of prep work must happen first. Best-in-class machine learning platforms need to be able to support these steps:
- Data ingestion and cleansing
- Data exploration and feature generation
- Model development and comparison
- Test and deployment.
Aite use their unique AIM evaluation methodology, which is driven by three major factors:
- Vendor-provided information based on Aite Group’s detailed AIM RFI document
- Participating vendors’ client reference feedback and/or feedback sourced independently by Aite Group
- Analyst analysis based on market knowledge and product demos provided by participating vendors.
The final results of their analysis are shown below:
Source & Copyright©2019 - Aite
The leading machine learning Adaptive Behavioral Analytics risk management company, Featurespace was recognized for its “best in class” product and ranked top overall in client service for its ability to provide robust service, support and value to clients. Featurespace also received exceptional recognition from Aite and its clients for:
- Model performance: "…head and shoulders above others tested… with a 63% reduction in false positives and a 177% increase in CardNotPresent fraud detection."
- Product performance: "Featurespace significantly outperformed four other leading machine learning platform vendors in a head-to-head value test…"
- Leading expertise "…since many fraud trends tend to hit Europe a few years before they come to the U.S., Featurespace was already solving problems that banks in the U.S. hadn’t seen yet."
CTMfile take: Machine learning is the way to go in fraud prevention.
Fraud prevention rates rise as cybercrime tactics evolve in Europe
High use of mobile devices and evolving fraudster tactics in Europe may be behind a rise in cybercrime attacks but rates of prevention and detection have increased 30 per cent year-on-year
Fraud prevention: latest research and tips
Telltale signs; contactless fraud; eyetracking technology; money laundering; cutting off terrorist funding; cost of fraud prevention
Fraud prevention report: use holistic approach & machine learning + beware DarkNet
Fraud prevention is a combination of processes and systems. Each company has to develop their own strategy for minimising fraud