Get fresh updates from Hortonworks by email

Once a month, receive latest insights, trends, analytics information and knowledge of Big Data.


Sign up for the Developers Newsletter

Once a month, receive latest insights, trends, analytics information and knowledge of Big Data.


Get Started


Ready to Get Started?

Download sandbox

How can we help you?

* I understand I can unsubscribe at any time. I also acknowledge the additional information found in Hortonworks Privacy Policy.
closeClose button
April 13, 2016
prev slideNext slide

Credit Card Fraud Prevention on a Connected Data Platform

The Hortonworks Connected Data Platform, serves as the unifying system for enterprises looking to power data processing and predictive analytic applications that leverage both Data In Motion along with Data at Rest with agility and flexibility.

The Data in motion capability is provided by Hortonworks Data Flow (HDF), which is powered by Apache NiFi.

HDF allows organizations to deliver instant insights by –

  1. Collecting, conducting and curating real-time data
  2. Providing end to end security with encryption and rules
  3. Data traceability with provenance capabilities

The Data at rest capability is provided by Hortonworks Data Platform (HDP), which is powered by Apache Hadoop.

HDP allows organizations to –

  1. Accumulating, Analyzing and Acting on all data
  2. Providing a centralized architecture for multitenant applications
  3. Supporting Enterprise Operations, Governance and security

Together these two platforms constitute a modern Connected Data Platform. The capabilities powered by the Connected Data Platform enable financial services organizations on their journey to critical business capabilities such as fraud detection.

Screen Shot 2016-04-08 at 8.37.27 AM

The Journey to Fraud Detection via a Connected Data Platform

At the 2016 Hadoop Summit in Dublin, we revealed a demo of how HDP can be used for credit card fraud detection.

While traditional fraud detection systems have focused on looking for factors such as bad IP addresses or unusual login times based on business rules and events, the Connected Data Platform renovates such an approach by enabling machine learning capabilities at scale. The journey as depicted below, involves helping customers with proactively identifying fraudulent transactions prior to the occurrence of fraud thus improving the customer experience.

Screen Shot 2016-04-08 at 8.37.39 AM

The Connected Data Platform

  1. Ingests both data in motion (customer transaction data, credit card swipes, online usage of credit cards etc.) & data at rest (core banking data, years worth of historical card data) using HDF.
  2. Performs Predictive Analytics. By commingling all kinds of data using machine learning techniques to do cardholder behavior running on HDP.
  3. Provide immediate fraud related feedback to the Bank and the Customer. The platform identifies and signals fraud in near real time. The result: an improved customer experience, revenue loss prevention due to fraud and reduced cost overall.

Solution Architecture…

The architecture of the overall demo solution as shown at 2016 Hadoop Summit in Dublin, is shown below.

Screen Shot 2016-04-08 at 8.38.30 AM

Advanced User Interface via Zeppelin Notebooks

Apache Zeppelin is leveraged to create a data driven & interactive user interface that enables advanced predictive analytics & visualization as depicted below.

Screen Shot 2016-04-08 at 8.39.39 AM

Ready to Dive In?

Access the repo and binaries for the demo

Leave a Reply

Your email address will not be published. Required fields are marked *