AI & UI Test Strategies for Intelligent Digital Ad Tech Platform
June 10 @ 10:00 am - 11:00 am MDTFree
In the bustling Ad Tech industry, we are constantly presented with challenges. These range from segmenting browsers, targeting devices, users (consumers) and even environments. Ad presentation specifications are constantly changing, as new devices are always coming onto the market. Machine Learning model techniques are adopted to engage and know the consumer preferences through ‘sentiment’ surveys or other polls. After performing automation on the newest (and oldest) mobile devices, a new connected TV device appears with unique challenges.
To conquer this, we follow a number of tests and techniques to handle the load, presentation, and user interaction. Define and develop a systematic and simple testing approach to analyze the machine learning data that use ‘models’ vs. ‘no models’ (test vs. control) and tunes the data. This presentation reviews some of those techniques such as machine learning model testing (“How many customers liked to purchase the advertised product”), A/B testing (“Determine whether changing the experience had a positive, negative, or no effect on the behavior”), UI testing (“How do the ads look under specified size players as per various targeting conditions”) and Automating the testing on multiple devices using Selenium (node js).
In addition, we will speak specifically to the audience about the automation benefits for all key areas in the Ad Tech platform.
- Define testing strategy for analyzing the ‘model’ and ‘no model’ machine learning historical data which increase the audience sizes for re-targeting by more than X times their current size, and will be a critical step to offer the best possible recommendations to its clients.
- How to set up automated tests to interact with expected behavior of media advertisements on various platforms.
- How to affirm coverage of the automated tests, identifying key areas in the Ad configuration or set-up that renders Ad as intended.
Naga Harini Kodey – QA Engineer, ViralGains Inc.
Naga Harini Kodey has 12+ years software testing experience in various organizations, including start-ups and Fortune 100 companies. She is currently working with ‘ViralGains Inc’ for over 3 years which is a leader in intelligent ad journey orchestration that uses Agile methodology. The ViralGains product as a (SaaS) platform built in Java/JEE serves consumers and marketers and focus on AI digital video advertising. Naga Harini Kodey has strong analytical skills and is very passionate in testing software applications, she is a gate keeper for quality deliverables in her organization.
She has strong understanding of QA methodologies and excelled in driving project deliverables. She has derived end to end functional and automation QA test plans for various projects that includes machine learning, UI and backend features. She has worked on multiple open-source automation frameworks that provide integration, functional, and visual testing. Naga Harini Kodey excels her passion for software test design and patterns by collaborating with multiple application teams across ViralGains to accelerate testing, mitigate risks, and increase the value of testing processes with test automation. She has efficiently managed production operations team being responsible for all technical aspects of application, maintaining the application, making sure the SLAs are met as per the customer requirements, built processes and tracked the defect backlog. She also has strong managerial and technical understanding of design and testing strategies of digital Media Ad and digital eCommerce projects.