A Temporal–Spatial network embedding model for ICT supply chain market trend forecasting

Market trend forecasting for the information and communication technology (ICT) supply chain strengthens external regulation. The existing models treat the influence weight and time granularity equally, ignoring the timeliness and accuracy of trading information, which influences the result of prediction. In addition, these methods do not consider the topological and sector hierarchical relationship of enterprises. In this work, a Temporal–Spatial hybrid market trend forecasting model (TSMTF) is proposed. First, in time domain instead of modeling time-varying transaction amount, transaction event probability prediction is modeled by Hawkes​ process. Furthermore, the attention mechanism is used to optimize the accuracy of weight allocation. Second, in spacial domain, the topological dependency relation between the different enterprises with transaction information, share information, and sector information is constructed by network embedding. The experimental results show that the model is superior to other baseline algorithms in ICT data sets. The effectiveness and applicability of this method are verified by ablation experiments and examples of products in the communication industry, and the model provides a practical tool for the external management of ICT supply chain market supervision.