Article: Research on anomaly detection in energy engineering bidding based on spatiotemporal graph neural network Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.38 pp.63 - 81 Abstract: The primary contribution of this study lies in its innovative approach to constructing a dynamic temporal graph for the multi-party entities and their interactions in energy project bidding, thereby capturing potential complex associations such as collusion and bid-rigging. Furthermore, a detection framework that integrates spatiotemporal graph neural networks with supervised learning techniques is proposed. This framework can simultaneously model the evolutionary patterns of bidding behaviour in the temporal dimension and the dependency patterns in the spatial dimension, enabling more accurate and efficient intelligent identification of concealed and dynamically changing abnormal bidding behaviours. Inderscience Publishers - linking academia, business and industry through research

Title: Research on anomaly detection in energy engineering bidding based on spatiotemporal graph neural network

Authors: Jinxuan Xiang

Addresses: Faculty of Law, Xiangtan University, Xiangtan, Hunan, 411105, China

Abstract: The primary contribution of this study lies in its innovative approach to constructing a dynamic temporal graph for the multi-party entities and their interactions in energy project bidding, thereby capturing potential complex associations such as collusion and bid-rigging. Furthermore, a detection framework that integrates spatiotemporal graph neural networks with supervised learning techniques is proposed. This framework can simultaneously model the evolutionary patterns of bidding behaviour in the temporal dimension and the dependency patterns in the spatial dimension, enabling more accurate and efficient intelligent identification of concealed and dynamically changing abnormal bidding behaviours.

Keywords: energy projects; bidding; anomaly detection; spatiotemporal graph neural network; discipline inspection and supervision.

DOI: 10.1504/IJICT.2026.153303

International Journal of Information and Communication Technology, 2026 Vol.27 No.38, pp.63 - 81

Received: 10 Sep 2025
Accepted: 02 Dec 2025
Published online: 01 May 2026 *

Title: Research on anomaly detection in energy engineering bidding based on spatiotemporal graph neural network

Keep up-to-date