Testing Large Data Sets with Supervised Machine Learning
Price rate is used to calculate an insurance premium based on the different insurance coverage. Every year the price rate is based on updated regulations, so after each change, the new price rate has to be tested for a large amount of data to make sure that the premium is correct based on the coverage. Testing fifty thousand data entries and their variations is impossible for any testing team. Alireza Razavi will present an AI automation testing framework designed to solve this testing problem. Discover how to use a supervised machine learning algorithm to determine the type of training examples, gather repressive training sets, select the input feature representation of the learned function, design the corresponding learning algorithm, run the learning algorithm on the gathered training set, and evaluate the accuracy of the learned function. This AI framework can be configured and adjusted for use in any testing scenario that requires testing of large data sets.
Alireza Razavi has more than 20 years experience as a QA director, Senior Advisor, and Practice Lead in organizations like; TD BANK, BNP PARIBAS BANK, National Bank of Canada, Montreal exchange. He has managed, defined, established norms, standard, best practices and governance strategy for different testing teams both on and off shore. Alireza has experience with test data management and information management, DevOps, continuous integration and AI best practices for testing and has worked on projects using BI, ETL and big data testing management, automation test management, AI automation frameworks, and performance test management.