Conference paper
A Hybrid Deep Learning Model for Dynamic Stock Movement Predictions Based on Supply Chain Networks
SSRN
Workshop on Information Technology and Systems (WITS), December 2020.
12/16/2020
Abstract
An inter-firm relationship of paramount importance is captured by supply chain networks. Embedded in such a network, a firm’s performance is associated with its partners’ and peers’ performance. This paper proposes an end-to-end predictive framework named Hybrid and Temporal Graph Neural Network (HT-GNN) to predict the dynamic stock price movement of firms. The model learns time-dependent node embeddings by aggregating network neighbors’ features and market trends to provide node classifications over time. Experiments on a real-world supply chain network among over 2,700 publicly traded firms show that HT-GNN can improve dynamic stock movement predictions. We define different types of network neighborhoods by identifying firms that contribute to such predictions in different ways and going even beyond immediate ties. Our results would naturally help investors understand stock price movement and managers identify network neighbors with predictive power over its own stock price movement.
Details
- Title: Subtitle
- A Hybrid Deep Learning Model for Dynamic Stock Movement Predictions Based on Supply Chain Networks
- Creators
- John RiosKang ZhaoW. Nick StreetHu TianXiaolong Zheng
- Resource Type
- Conference paper
- Conference
- Workshop on Information Technology and Systems (WITS), December 2020.
- Publisher
- SSRN
- Number of pages
- 15 pages
- Language
- English
- Date published
- 12/16/2020
- Academic Unit
- Business Analytics; Nursing; Computer Science; Bus Admin College
- Record Identifier
- 9984380748402771
Metrics
7 Record Views