Title: Predicting enhancement in knowledge level with random forest machine learning algorithm

Authors: Niharika Agrawal; Faheem Ahmed Khan; G.A. Lalithamma

Addresses: Department of Electrical and Electronics Engineering, Ghousia Institute of Technology for Women, Bangalore – 560029, Karnataka, India ' Department of Electrical and Electronics Engineering, Ghousia Institute of Technology for Women, Bangalore – 560029, Karnataka, India ' Department of Electrical and Electronics Engineering, Rajiv Gandhi Institute of Technology, Bangalore – 560032, Karnataka, India

Abstract: The objective of this research is to create a machine-learning-based approach that is efficient for predicting and assessing the success of students' learning. This is significant because it helps predict students' intellectual comprehension. It helps educators identify underachievers and take the necessary steps to improve students' knowledge. To develop a strong and successful nation, the learning outcomes of students must be very high. Bloom's Taxonomy, a helpful instrument for educators, provides a structure for developing challenging lessons that optimise student advancement. This manuscript ascertains the student's knowledge level ('high' or 'low') based on the inputs (class study time and home repetition time) with the aid of the random forest algorithm (RFA). The accuracy of prediction is 98% with RFA. Intelligence can be developed or strengthened by spending quality study time. This study helps to fulfil the fourth Sustainable Development Goal (SDG) and cultivate the next generation of national leaders.

Keywords: algorithm; dataset; educator; family; nation; output; parent; quality; subject; student; study; time.

DOI: 10.1504/IJLC.2025.146618

International Journal of Learning and Change, 2025 Vol.17 No.2, pp.157 - 184

Accepted: 28 Oct 2024
Published online: 06 Jun 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article