Examination plays an important role in testing the student?s knowledge. The conventional style of creating, preparing, and generation of test questions manually is intriguing and cumbersome. In this study, we introduce an automated questionnaire generation system that uses a hybrid approach using Na?ve Bayes (NB) and Las Vegas Algorithm (LVA). LVA is a randomized algorithm by Laslo Babai that always produces a correct result but has a running time that is based on a random value. While NB is one of the most well-known data mining algorithms for classification.