Table 3 Features and descriptions.

From: Navigating cognitive boundaries: the impact of CognifyNet AI-powered educational analytics on student improvement

Feature

Description

Student_ID

Each student is assigned a unique alphanumeric identifier, ensuring that individual records are distinguishable and traceable without using personally identifiable information.

Age

The student’s age in years allows analysis of performance variations across different age groups, which may correlate with maturity, experience, and cognitive development in learning contexts.

Gender

The student’s gender is recorded to examine gender-related trends in learning behaviours and outcomes, which may reveal insights into gender-specific support needs or learning preferences.

Previous_Exam_Score

The student obtained the most recent exam score before the current assessment period. This feature serves as a baseline for evaluating improvement or decline in academic performance over time.

Hours_of_Study

The average number of hours the student dedicates to study per week indicates their level of engagement and effort outside of formal classroom settings, which often impacts academic achievement.

Attendance_Percentage

The student’s attendance rate is expressed as a percentage of total classes attended. High attendance often correlates with increased access to learning resources, greater consistency, and stronger academic performance.

Cognitive_Improvement_Score

A composite score reflects changes in the student’s cognitive abilities, such as critical thinking, problem-solving, and memory retention, measured through assessments or cognitive tests. This score helps gauge learning growth.

Student_Performance_Score

The overall academic performance score encompasses grades from various assessments, assignments, and exams. This feature acts as the target variable for prediction, helping to identify students who may benefit from tailored interventions.