Using Imply to prevent fraud
Fraud is a multi-billion dollar problem facing everyone from banks to credit card issuers to payment processors to merchants. Detecting and preventing fraud has traditionally been a challenge for these types of businesses, who rely on a clunky combination of heuristic-based rule engines and home-grown analytics solutions. In this talk, Danny D. Leybzon will be presenting a new methodology for anomaly detection and analysis that can be applied to everything from fraud detection to factory accident prevention. This system uses a combination of the Imply analytics platform (built on top of the open source Apache Druid) and the anomaly detection system Sherlock (built on top of the open source Yahoo EGADS). It leverages both human and machine expertise, allowing both actors to play to their strengths, while offsetting each other's weaknesses.
Imply is a real-time data platform for cost-effective, low-latency analytics. Uniquely, it provides consistent sub-second response to ad hoc queries against PB-scale data, even with high user concurrency. Imply is used for clickstream analytics, application, network and service performance monitoring, IoT analytics, fraud detection and more. Imply powers user-facing analytics applications and serves as a backend for highly-concurrent APIs. Companies such as Twitter, Charter (Spectrum), Twitch and DBS (Southeast Asia’s largest bank) trust Imply to put analytics into the hands of their trained analysts and non-technical business people.
Connect
Website: https://imply.io/
Linkedin: / impl...
Twitter: / implydata
Github: https://github.com/implydata
Slideshare: https://www.slideshare.net/implydata