A Novel Approach for Lookalikes with Multi-Level Sub-Category on Large-Scale Data

Authors(s): Thejaswini P, Kiranmayi KL Chandra

Abstract

Lookalike audience generation is an effective way to increase the audience base in online advertising. Segregating the lookalike audience into multiple priority levels gives greater flexibility to the advertiser in selecting their user reach. In this paper, a novel approach of lookalike audience generation in multiple priority levels on a large-scale data with millions of users and thousands of audience segments is explained. An automated system combining custom models to generate similar audience segments and group lookalike audience into priority levels using Spark Scala and Hadoop ecosystem is developed. The experimental results comparing different approaches show that our proposed model outperforms others in reach, scalability, and speed.

The Chartered Data Scientist Designation

Achieve the highest distinction in the data science profession.

Explore more from Association of Data Scientists

Become ADaSci Chapter Lead

As a chapter lead, you will have the opportunity to connect with fellow data professionals in your area, share knowledge and resources, and work together to advance the field of data science.