English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Forecasting future stock trends remains challenging for academia and industrydue to stochastic inter-stock dynamics and hierarchical intra-stock dynamicsinfluencing stock prices. In recent years, graph neural networks have achievedremarkable performance in this problem by formulating multiple stocks asgraph-structured data. However, most of these approaches rely on artificiallydefined factors to construct static stock graphs, which fail to capture theintrinsic interdependencies between stocks that rapidly evolve. In addition,these methods often ignore the hierarchical features of the stocks and losedistinctive information within. In this work, we propose a novel graph learningapproach implemented without expert knowledge to address these issues. First,our approach automatically constructs dynamic stock graphs by entropy-drivenedge generation from a signal processing perspective. Then, we further learntask-optimal dependencies between stocks via a generalized graph diffusionprocess on constructed stock graphs. Last, a decoupled representation learningscheme is adopted to capture distinctive hierarchical intra-stock features.Experimental results demonstrate substantial improvements over state-of-the-artbaselines on real-world datasets. Moreover, the ablation study and sensitivitystudy further illustrate the effectiveness of the proposed method in modelingthe time-evolving inter-stock and intra-stock dynamics.

DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Prediction