Argyle Data, a real-time fraud analytics startup, has rolled out its flagship anti-fraud software, alongside an announcement of $4.5 million in funding to help companies detect and combat fraud through machine learning and real-time analytics.
Dubbed AgyleDB, the application taps NSA’s open source Accumulo database technology to “perform deep-packet inspection and create massive databases from that data,” while using Facebook’s Presto SQL query engine to let users analyze that data stored in Hadoop and “automate future queries against live data,” reports GigaOm.
Statistics reveal that mobile communication companies alone lose more than $46 billion each year, while 53% of financial services organizations take up to 8 hours to detect fraud, resulting in billions lost. One of the major problems with fraud detection is the turnaround time. Most fraud detection systems in use today take 24 hours or more to detect fraud attacks, creating a window of opportunity that gives fraud perpetrators the opportunity to steal millions from businesses and individuals. Reducing the time between when fraud happens and when it’s detected could save companies billions of dollars, explains Argyle Data in a statement announcing the recent developments.
“Argyle also uses machine learning algorithms to detect fraud patterns across datasets much too large for humans to make sense of themselves,” writes Derrick Harris of GigaOm. “A big, scalable open source platform like Hadoop for storing data is great, but big, scalable, open source analytic technologies on top of Hadoop start to open up a lot more possibilities,” he added.
Complete our SAP x Data Natives CDO Club survey now, and help us to help you
Argyle Data will also have four new executives joining their team – Arshak Navruzyan, Dr. Ian Howells, Padraig Stapleton, and Dr. Volkmar Scharf-Katz. With a combined background in machine learning, marketing, mobile communications and big data at giants like AT&T and Vodafone the startup hopes to bolster its product development as well as outreach.
Read more here.
(Image credit: Jonathon Colman)