Multimodal multiscale dynamic graph convolution networks for stock price prediction

Ruirui Liu, Haoxian Liu, Huichou Huang, Bo Song, Qingyao Wu

Abstract: Highlights•We propose a novel Multiscale Multimodal Dynamic Graph Convolution Network.•The MMFDB effectively extract and align rich multimodal feature representations.•The STGCL are powerful in learning complex relations simultaneously.•Extensive experiments justify the superior performance of our proposed model.