Enhancing Educational Assessment: Predicting and Visualizing Student Performance using EDA and Machine Learning Techniques

Abstract

Educational institutions must manually evaluate student's performance, which requires a significant amount of faculty time and effort. Teachers can easily monitor and document student's learning behavior if they utilize a learning management system (LMS). It can be utilized by coaching sessions or educational institutions to quickly analyze student's performance. Due to the enormous number of pupils, huge data must be analyzed; teachers frequently encounter challenges. The qualities of learners who are students are described analytically in this analysis. In this work, student's cognitive and psychomotor skills are predicted and visualized using Exploratory Data Analysis (EDA) and Machine Learning techniques like KNN and Multiple Regressions. The maximum accuracy of 99% has been obtained in Multiple Regression.