About this document
Hierarchical Attention Capsule Network for Stock Prediction by Susmitha Prince is a document available to read on EtoBox.
This document proposes a multi-element hierarchical attention capsule network (MHACN) for stock prediction that consists of two components. The first component is a multi-element hierarchical attention model that quantifies the importance of information from multiple news and social media sources. The second component is a capsule network that learns more context information from events. Experiments show the MHACN model improves prediction accuracy by accounting for different influences of events on stock p
- Author
- Susmitha Prince
- Language
- EN