Improving Automated Testing Accuracy with Machine Learning
Test automation, especially at the User Interface(UI) level, is fragile. In Autodesk Localization department, there is a very significant overhead in time to manually verify results from automated user-interface testing tools. Over the last year, we have been developing a Machine Learning model to automatically predict results from our automated testing tools, leading to a very significant drop in the number of tests we need to verify manually. In this webinar, Justin and Mirjana will share details of the problem, and how they put together a new test-results management system with integrated Machine Learning that learns from previously manually verified result
- Automated User Interface testing – where it’s useful and where there are drawbacks
- How Machine Learning can be used to improve reliability of automated testing
- Potential challenges and solutions to using Machine Learning in automated testing
Justin Lawler | Senior Software Developer | Autodesk
Justin is a developer with over 18 years of experience in the tech industry. Currently working in Autodesk’s Localization team, he has a background in full-stack development including microservices and functional programming. Justin is now involved in developing the Autodesk platform and building Artificial Intelligence into the localisation processes to optimize time to market.
Mirjana Radovanov | Senior Software Developer | Autodesk
Mirjana is senior software developer, currently working in Autodesk Localization team. She has 20 years of experience in software development, in telecommunications, software and financial companies. Originally from Serbia, Mirjana lives in Dublin, Ireland for 18 years. In Autodesk Mirjana works as LE project lead for civil engineering Autodesk products and is a software developer in Artificial Intelligence Initiative.