Predicting Student Performance with Machine Learning Algorithms
Pratap Patil, Naina Chaudhary, Sujit Prasad, Mohit Bhandwal, Manik Arora, Kulbir Singh
Abstract
This paper aims to explore the effectiveness of JFLAP as a pedagogical tool for automata theory and its impact on student performance. We implement machine learning algorithms to predict and analyze the improvement in students' understanding and performance, utilizing data gathered from exercises, simulations, and assessments conducted within the JFLAP environment. The objective is to identify the correlation between the use of interactive learning tools and enhancement in conceptual grasp, problem-solving skills, and academic performance. We will adopt a comprehensive approach, employing both qualitative and quantitative methods to glean insights into the multifaceted impacts of JFLAP on student learning outcomes. The quantitative data, derived from scores, completion times, and progress tracking within the JFLAP system, will be supplemented by qualitative data sourced from surveys, interviews, and observational studies. This blend of data types will facilitate a nuanced understanding of not just the measurable improvement in academic performance, but also the subtle yet significant enhancements in students' cognitive abilities, engagement levels, and overall interest in automata theory. Furthermore, the integration of machine learning models will enable us to identify patterns and trends, providing predictive insights and personalized recommendations to foster a more tailored and effective learning experience for each student.