Addressing the Needs of Slow Learners in Engineering Programs: Effective Identification and Improvement Strategies

Abstract

This paper addresses the needs of slow learners in engineering programs by exploring effective identification and improvement strategies. We employ a range of statistical methods, including descriptive statistics, regression analysis, and clustering, to identify slow learners. Predictive modelling techniques, such as decision trees and support vector machines, are utilized to classify students based on their learning patterns. Our analysis with Python Programming reveals a noticeable improvement in academic performance from Semester 1 to Semester 2. Specifically, there is an increase in average CGPA, a decrease in the number of backlogs, and an improvement in the passing rate. These results demonstrate the effectiveness of the implemented strategies. To support these learners, we propose several strategies: pairing slow learners with advanced peers, promoting peer teaching, developing individualized learning plans, and utilizing technology-enhanced resources. Feedback from students indicates high satisfaction with these strategies, reflecting their positive impact on engagement, understanding, and academic performance. These approaches collectively aim to foster better learning outcomes and overall improvement in engineering education.