case study / Marketing Technology / Machine-learning Optimization Technology

Machine-learning Optimization Technology

Anticipating wants & needs with predictive marketing.

Challenge

  • Client experienced high demand for complex new features that were a key revenue generator. In particular, how to reach the right person (sales target) with a personalized ad message during the moment of influence. Client needed to increase application performance, renovate build and infrastructure, while introducing modern QA practices.

Overview

Our client is a predictive marketing software company that uses artificial intelligence to empower agencies and marketers to anticipate people’s needs for products and services. The platform combines the science of artificial intelligence with the scale of big data to improve the effectiveness of programmatic marketing.

Solution

  • Completed the migration of business-critical admin application that and had many functionalities, e.g. different types of targeting, ads preview, viewability pixels, etc.
  • Dynamic Creative Tools for self-service clients providing building, customizing, and trafficking ads based on Dynamic Creative templates.
  • Native ads creation and serving through recommendation widget or in-feed.
  • Top Insights tool offers easy-to-understand visuals that help users quickly identify the behavioral, contextual and campaign attributes that are having the most impact on campaign performance:
    • Significantly improved overall app performance, such as fixed UI performance issues (rendering, tabs, view refactoring etc.), executed SQL query optimization, DB schema refactoring, moved logic to a server, etc.
  • Implemented testing of data transformation pipelines (map/reduce using Hive to Vertica), developed and integrated automation infrastructure for deployment and testing data transformation pipelines using Jenkins.

Results

  • Accelerated our client’s ability to evolve quickly and maintain leading position in the market:
    • Enabled our client to improve process by introducing Scaled Agile Methodology with focus on business value, fast feedback and recommended building teams based on value streams.
  • Modernized build and test infrastructures:
    • Took ownership over testing
    • Creation of automation tests
    • Target release regression testing
    • Data integration testing
    • Bidder functional testing

Talk To Us

Let’s talk about how Lohika can help you scale your engineering organization.