Article: Multidimensional assessment of employment competence of Jiangxi graduates by BPNN Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.49 pp.19 - 37 Abstract: As the scale of university graduates has continued to expand, the evaluation of employability has become a critical issue in higher education management and talent cultivation. This study aimed to develop a scientific, quantitative, and multidimensional method for assessing graduate employability. An employability indicator system was constructed using the analytic hierarchy process (AHP). The results indicated that professional competence had the highest weight (0.55). Within this dimension, technical operation and experimental skills, the application of theoretical knowledge, and the quality of project experience contributed most significantly to employment competitiveness. A back propagation neural network (BPNN) model was further applied to train and predict the sample data. The results demonstrated a high level of consistency between the predicted values and the actual values. The absolute error ranged from 0.03 to 0.11, the relative error remained below 2.12%, and the overall accuracy reached 0.926. Universities should strengthen professional practice and innovation capacity development and given to enhancing students' professional qualities to improve overall employment competitiveness. The main contribution of this study provides a decision-making reference for higher education management, career guidance, and policy formulation. Inderscience Publishers - linking academia, business and industry through research

Title: Multidimensional assessment of employment competence of Jiangxi graduates by BPNN

Authors: Kaiqiong Chen; Jacquline Tham; Ali Khatibi

Addresses: Jiujiang Polytechnic University of Science and Technology, Gongqing City Gongqing Avenue 1, Jiujiang City, 332020, Jiangxi Province, China ' Postgraduate Centre, Management and Science University, Shah Alam, Selangor Darul Ehsan, 40100, Malaysia ' Postgraduate Centre, Management and Science University, Shah Alam, Selangor Darul Ehsan, 40100, Malaysia

Abstract: As the scale of university graduates has continued to expand, the evaluation of employability has become a critical issue in higher education management and talent cultivation. This study aimed to develop a scientific, quantitative, and multidimensional method for assessing graduate employability. An employability indicator system was constructed using the analytic hierarchy process (AHP). The results indicated that professional competence had the highest weight (0.55). Within this dimension, technical operation and experimental skills, the application of theoretical knowledge, and the quality of project experience contributed most significantly to employment competitiveness. A back propagation neural network (BPNN) model was further applied to train and predict the sample data. The results demonstrated a high level of consistency between the predicted values and the actual values. The absolute error ranged from 0.03 to 0.11, the relative error remained below 2.12%, and the overall accuracy reached 0.926. Universities should strengthen professional practice and innovation capacity development and given to enhancing students' professional qualities to improve overall employment competitiveness. The main contribution of this study provides a decision-making reference for higher education management, career guidance, and policy formulation.

Keywords: back propagation neural network; BPNN; neural network model; university graduates; employability.

DOI: 10.1504/IJICT.2026.153621

International Journal of Information and Communication Technology, 2026 Vol.27 No.49, pp.19 - 37

Received: 26 Nov 2025
Accepted: 12 Jan 2026
Published online: 18 May 2026 *

Title: Multidimensional assessment of employment competence of Jiangxi graduates by BPNN

Keep up-to-date