Autonomously and continuously identifies patterns and context in data from people, machines, devices, sensors
Stores knowledge of the connections between concepts—including the number, frequency, closeness, and context of those connections
Automatically finds patterns of similarity, classifications, convergence, anomaly and novelty in data—learning and adapting as new data and feedback arrive in real time
Provides transparent, explainable, auditable results that go beyond black-box models to help make better business decisions
Anti-Money Laundering (AML) regulations require financial institutions to know their customers and report suspicious behavior to the federal government. Rather than looking for behavior that matches certain rules (which require frequent updates), Intel Saffron's cognitive AML solution autonomously detects anomalous behavior among customers and their transactions - leading to fewer false positives reports, improved investigator efficiency, and reduction in regulatory compliance costs.
The speed and sophistication at which new fraud techniques are emerging create major challenges for today’s banks and insurance companies. For insurers, Intel Saffron’s cognitive solution provides a single view of all associations across existing and past claims - helping detect previously discovered fraud rings and avoid unnecessary and costly payouts.
The more personalized and relevant experiences financial institutions can create for their customers, the better they can affect retention rates. Intel Saffron looks across customer and transaction data and surfaces actionable insights that help financial institutions recommend the right product or service to the right customer at the right time to increase customer satisfaction, improve revenue and prevent customer churn.