Title: Network big data association recommendation method based on modified entropy and improved FCM algorithm

Authors: Xiaomin Liu

Addresses: School of Mathematics and Physics, Bengbu University, Longzihu District, Bengbu, Anhui Province, China

Abstract: In order to overcome the problems of low accuracy, low recall and long generation time of recommendation results in traditional recommendation methods, a network big data association recommendation method based on modified entropy and improved FCM algorithm is proposed. Calculate the information entropy of network data and correct it. Use the corrected entropy to perform dimensionality reduction on the data. Calculate the abnormal factor value of the network data after dimensionality reduction to detect and remove abnormal data. Use an improved FCM algorithm to cluster the data after removing anomalies. Build a CLUPCDR model through data augmentation module, user feature extraction module and mapping header module, and use this model to implement network big data association recommendation. The experimental results show that the maximum accuracy of the proposed method is 98.74%, the maximum recall is 99.12%, and the recommended result generation time varies between 0.19 s and 0.57 s.

Keywords: corrected entropy; improved FCM algorithm; network big data; association recommendation; abnormal factor value; CLUPCDR model.

DOI: 10.1504/IJIPT.2025.147121

International Journal of Internet Protocol Technology, 2025 Vol.18 No.1, pp.48 - 57

Received: 20 Dec 2024
Accepted: 20 Feb 2025
Published online: 10 Jul 2025 *