Title: Optimisation of network learning platform based on machine learning algorithm

Authors: Jin Zhang

Addresses: Nanchang Institute of Technology, Nanchang, Jiangxi, China

Abstract: The purpose of this study is to optimise online learning platforms through deep learning and address issues related to personalised user experience and resource allocation. A comprehensive optimisation framework is proposed, comprising three modules: user behaviour analysis, personalised recommendation and resource optimisation scheduling. First, a recommendation mechanism is developed by integrating Neural Collaborative Filtering (NCF), the Transformer model and Content-Based Filtering (CBF) techniques. Accordingly, a user behaviour prediction and personalised recommendation model based on a fused NCF-CBF-Transformer algorithm (NCF-CBF-T) is constructed. This model enhances the personalised recommendation system by leveraging multi-level technology integration. Specifically, the Transformer model captures temporal dependencies in user behaviour sequences and dynamically models long-term user interest evolution through the multi-head self-attention mechanism. This study contributes to the theoretical advancement of deep learning applications in educational technology and provides practical experimental references for optimising online learning platforms.

Keywords: network learning platform; machine learning; personalised recommendation system; transformer; user behaviour prediction; resource optimisation scheduling.

DOI: 10.1504/IJCAT.2025.149866

International Journal of Computer Applications in Technology, 2025 Vol.77 No.1/2, pp.85 - 101

Received: 05 Mar 2025
Accepted: 04 Jun 2025
Published online: 14 Nov 2025 *

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