Fuzzy Logic Expert System for Analyzing Student Performance

Assessing the effectiveness of academics at various tiers has grown progressively difficult when employing traditional approaches that predominantly depend on numerical ratings to gauge their teaching and research accomplishments. With the indexing of academic performance in international databases using impact indices at various scales, the demand for advanced computer models has arisen. In this study, we suggest employing expert systems that utilize fuzzy logic to tackle the evaluation of educators, even when confronted with imprecise data and uncertainties. As a novel contribution, this research develops a fuzzy logic model and implements an algorithm using Python and Anaconda, which allows for fuzzy logic rule inference and comprehensive analysis. The implementation of the system is done using Python and leveraging Anaconda's data science environment, providing a seamless and efficient development process. The results of this pilot study involve testing and validating the proposed model through a user-friendly graphical interface, providing comprehensive insights based on minimum criteria along with additional explanations. This approach opens up new possibilities for more accurate assessment of academic performance, particularly when dealing with ambiguous data and uncertain conditions.