Transamerica sells a wide array of products in the insurance, investment, and retirement spaces. Due to the complexity and variety of the company’s products, selecting the right product to serve a given customer’s needs is a challenge. Transamerica’s engineering team built a recommendation engine to guide the customer and simplify the buying experience. The company’s recommendation engine is also leveraged by Transamerica’s marketing and customer-service teams to optimize cross-sell and upsell offers.
In particular, the team developed a customer data hub providing a 360-degree view of the customer on Cloudera’s Hadoop platform with data feeds from all of Transamerica’s administration systems. Recommendation models were built using the H2O machine-learning platform on Transamerica’s customer data hub. Vishal Bamba, Nitin Prabhu, Jeremy Beck, and Amy Wang highlight the architecture of the customer data hub and focus specifically on Transamerica’s machine-learning models and the data challenges that the engineering team faced.
Vishal Bamba is vice president of strategy and architecture at Transamerica Technology, where he leads a team focusing on innovation initiatives within the enterprise. Vishal has over 15 years of experience in distributed systems and has led many innovation projects. He has consulted and worked for several companies including Disney, Getty, Northrop, and AIG/SunAmerica. Vishal holds an MS in computer science from the University of Southern California.
Nitin Prabhu has been with Transamerica for over a decade in IT roles. He now serves as manager for strategy and architecture.
©2016, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.