The ai Corporation (ai), an FCA approved expert in payment and risk management, today announced the addition of exploratory data analysis (EDA) and impact analysis functionality to its automated machine learning solution.
The enhanced learning functionality builds on ai’s award winning, self-service, fraud detection solution. Enabling more organisations to create an end to end, automated fraud strategy, and giving existing users the opportunity to test their entire fraud strategy, before production and deployment, in an industry first.
Dr. Mark Goldspink, CEO at The ai Corporation, says: “ai has raised the bar by combining EDA and Impact Analysis with our automated fraud detection solution. The combination is unique and provides our users with a self-service solution, which detects more fraud, reduces false positives and greatly improves back office efficiency for fraud strategy definition.
“Payment fraud is a growing global problem, with card fraud loss expected to rise to $45 billion by 2025. ai’s enhanced solution allows organisations to benefit from fully automated fraud detection, that compliments their existing systems. While helping them to become more profitable. Driving back-office efficiencies and reducing fraud losses.”
How ai combines EDA and Impact Analysis
EDA is the first process in the automated fraud strategy definition journey. EDA finds fraud hotspots and problem areas. Suspicious patterns can then be detected in a live system with ai’s SmartScore® model or SmartRule® rule set generator tools. EDA streamlines the manual data discovery task, finding fraud-rich data sets in hours, realising huge savings over the manual task/generator tools.
Impact Analysis shows how SmartScore® neural models and SmartRule® rule sets behave together in a safe offline environment, so the fraud manager can be assured of their performance. The tool enables fraud managers to quickly build, and test, new fraud strategies, without the threat of affecting fraud losses.
How ai’s machine-learning technology works
ai’s SmartSuite of machine-learning technology gives banks the power to automatically create effective fraud rules which can be implemented into any fraud platform, including ai’s rules engine RiskNet®. By using machine-learning, banks can automate their fraud prevention, mitigating ACH fraud regardless of how it is perpetrated including account takeover, ‘man in the middle’ fraud and/or social engineering.
SmartScore®, one of six products within ai’s SmartSuite, creates neural models using artificial intelligence and automated machine-learning techniques, to recognise patterns and trends in fraud. Providing transaction risk scores to be used in conjunction with user-defined rules.
With its unique multi-model capabilities, SmartScore® enables users to create Neural Models specific to a fraud type, customer segment or payment method, including ACH. By constantly refreshing the data available, SmartScore® provides an up to date and accurate risk score based on current trends, ensuring that RiskNet® or any third-party fraud platform users are not reviewing unnecessary alerts.