Seite - 136 - in The Future of Software Quality Assurance

136 G.Numan 3. Writing testcases: per user group input with expected top result, not expected, metrics andweight 4. Running test cases in AIsystem(searchengine) 5. Processing results 6. Creating test resultsper test casewith overallweighing 7. Comparingresultswith results frompreviousversion 5 Conclusions The world of AI is very dynamic: the algorithm does not equal the code but is a result of trainingdata and labelling.Trainingdata will be updatedconstantlyas the world changes. The output of AI is not Boolean but calculated results on all labels whichcouldallbe relevant. Despite lowtransparencyandrisks inBias,AI isbeingusedfordecisionmaking and is an important part of people’s worlds. Testers must play a role in creating transparency, by identifying user groups and their specific expectations and needs and showing how the system reflects these. For this purpose an automated test framework is needed to compare the many versions of the AI system, monitor quality in productionconstantlyandgiveguidance tooptimisation. An AI tester needs skills in data science but most of all moral and social sensitivity! Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation,distributionandreproduction inanymediumorformat, as longasyougiveappropriate credit to the original author(s) and thesource, provide a link to theCreative Commons licence and indicate if changes were made. The images or other third party material in this chapter are included in the chapter’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the chapter’s Creative Commons licence and your intended use is not permitted by statutory regulation orexceeds the permitteduse, you willneed toobtain permission directly from the copyright holder.