Attendance-Based Prediction of Learning Outcomes via Linear Regression

This study investigates the influence of class attendance discipline on student learning outcomes. The primary objective is to determine the effect of student attendance on learning outcomes by analyzing attendance and grade data. The dataset is derived from recorded class attendance and student grade data. This data is processed to obtain a Learning Quality Index (LQI) and a Results Quality Index (RQI), based on predefined weighting criteria. These indices are then combined to form a comprehensive research dataset. A simple linear regression method is employed to analyze the relationship between the LQI and the RQI. The regression model uses the Results Quality Index (RQI) as the dependent variable (Y) and the Discipline Quality Index (DQI) as the independent variable (X). The findings indicate that 82% of the variation in student grades can be attributed to the level of attendance discipline, with the remaining 18% influenced by other factors. The coefficient of determination (R²) is 0.67, implying that the predictor variable (DQI) explains 67% of the variance in the response variable (RQI), while the remaining 33% is explained by other variables. This research underscores the significant impact of attendance on academic performance and suggests that further studies should consider additional factors to enhance predictive accuracy.

I. Introduction

The background of this study is the significant role of learning activity data in providing precise information that helps students succeed through early detection. This data allows educators to estimate factors that significantly contribute to student performance and develop appropriate strategies to prevent undesirable outcomes [1], [2], undesirable [3]. Several educational institutions have responded to this by assessing students, using various forms of assessment [4], [5]. Several research facts that utilize student attendance data in learning can provide detailed information about student learning, so that they are able to define and identify behavioral patterns related to student learning outcomes [6], [7], [8].