Customer

This company is a leader in fraud prevention and risk management. They provide financial institutions and customers with fraud and risk management tools, facilitate a secure exchange between financial organizations and offer solutions for responding quickly to evolving fraud challenges.

 

Business Challenge

This customer was looking for a solution to detect fraud in real-time for mobile payments and check deposits. They required high-availability to assure 24X7 access for demanding customers.  Reducing their current TCO was also a priority.

• Detecting fraud on mobile payment applications in real-time
• Detecting the deposit of the same check-in multiple accounts at different banks in real-time
• User experience: application availability 24×7
•  TCO reduction: reduce dependency on expensive RDBMS

 

Technical Challenge

• Required  ingestion of  4 TB of data daily
• Support of fully consistency for transactional in-memory map-reduce
• Millisecond response
• Ability to analyze and validate against a large dataset of live (multiple TB) in memory and archived data (to Cassandra NoSQL and Hadoop)

Solution

The GigaSpaces in-memory real-time analytics platform provides sub-second response for accurate fraud detection to stop the transaction before it is completed. The high-performance solution ingests 4 TB daily and handles over 1.5M events per second. TCO was reduced when introducing RAM and SSD, replacing expensive alternatives. No-Downtime is assured with a fault-tolerant, highly available, scaling on-demand solution.

 

Results

• Sub-second response for accurate fraud detection to stop the transaction
• 1.5M events per second
• TCO Reduction: RAM and SSD for runtime data compared to alternative solutions
• Fault-tolerant, highly available, scaling on demand