My Journey Testing ML-Based RecommendationsInvited speaker
In today‘s era, machine learning (ML) is indeed the epicenter of software. Most software applications have ML-based components, with one such common component being recommendations. Tremendous effort is put into developing such recommendation systems. But have you ever wondered how these systems are tested? Much of the time, quality can take a backseat here as people perceive that It‘s machine learning, it cannot be tested. But is that really the case? If not, how can we break this myth?
Join Shivani Gaba as she shares her journey on exploring and testing recommendation systems, without having any prior experience of it. She‘ll reflect on her motivation, challenges faced and learnings. Not only will you get an introduction to the big picture and basic components of ML recommendation systems, but you‘ll also learn how product knowledge and thinking out of the box makes a difference. Shivani will leave you with tips, tricks, and techniques on how to create an impact on quality in such projects.
- Importance of testing ML-enabled applications
- Advised practices of testing recommenders
- How to apply product knowledge to test recommenders
- Testability of ML recommender models
Shivani Gaba, New Work SE
Shivani Gaba is a passionate QA Engineer who believes that knowledge sharing boost up all engaged parties and increases their confidence. It was summer of 2013 when Shivani and testing met each other for the first time and have been best friends since then. Holding rich experience in testing domain, she currently works as Senior QA Engineer with XING (the largest business network in German speaking countries).
With hands-on experience in all layers of software testing ranging from UI (frontend), API and backend, functional, non-functional , mobile testing – API remains her all-time favorite. As a certified scrum master, working in an agile manner is always her approach. She believes in the idea of spreading her findings about any new fancy stuff she learns. She has worked with multiple international teams and brings forward the idea of the whole team contributing to quality. She‘s always up for conversation over email, LinkedIn, Xing, twitter or the beer table :)