Finite predicate-driven logic networks method for enhanced education data analysis

Abstract

The subject matter of the study is intelligent data analysis in the field of academic information. The goal of the study is to create a mathematical model for analyzing students' academic information using the predicate-driven logic networks method, which allows taking into account both logical dependencies and probabilistic transitions between states. To achieve this goal, the following tasks were defined: analysis of the theoretical foundations of the logic networks method and predicate logic, integration of these approaches into a single mathematical model, development of approaches for its application in academic data analysis problems. The research used the methods of mathematical modeling, complex logical analysis, and method for constructing logic networks. The following results were obtained: a theoretical model was developed that integrates the principles of logic networks and predicate logic for analyzing student academic performance; the model accounts for both probabilistic transitions between states and logical dependencies among student parameters; the mathematical model also incorporates logical rules to enhance the accuracy of logical analysis within the academic context. The model was tested on a dataset of student performance, demonstrating its effectiveness in accurately predicting academic outcomes and confirming the validity of the integrated approach. Conclusions. The scientific novelty of the results obtained is as follows: 1) a theoretical model for analyzing student academic data was developed by integrating logic networks and predicate logic, allowing for the simultaneous consideration of probabilistic transitions and logical dependencies among student parameters; 2) the approach enhances the analysis process by incorporating logical rules into the probabilistic framework, providing a more nuanced and accurate tool for analyzing academic data; 3) this combined model offers a novel method for addressing complex logical analysis tasks in educational settings, paving the way for further research and practical applications in intelligent data analysis. The successful testing of the model on actual student data further underscores its potential as a powerful tool in educational data analysis.