Advanced Examination Systems: Applying Fuzzy Logic and Machine Learning Methods in Education

In our paper, we present an innovative educational assessment system that attempts to overcome the limitations of traditional educational evaluation methods by applying machine learning, artificial intelligence, fuzzy logic, and advanced mathematical techniques. This system can provide a more objective and personalized assessment of students’ knowledge. Current examination systems in educational institutions are outdated and do not meet modern societal and technological requirements. A central element of the system is the application of fuzzy logic, which allows for handling uncertainties in knowledge assessment. Using the FP-growth algorithm and the fuzzy analytical hierarchy process (AHP) aids in optimizing the evaluation process and enables a more profound analysis of students’ performance. During the system's development, we aim to adaptively manage the difficulty level of questions, taking into account students’ prior performance and individual capabilities. The study highlights the security risks and efficiency issues of current “manual” question compilation methods. The new system aims to minimize these risks while improving the quality of education and reducing the workload of educators.