https://scholars.lib.ntu.edu.tw/handle/123456789/580602
Title: | Stock Movement Prediction That Integrates Heterogeneous Data Sources Using Dilated Causal Convolution Networks with Attention | Authors: | Daiya D Wu M.-S CHE LIN |
Keywords: | Audio signal processing; Convolution; Convolutional neural networks; Finance; Financial data processing; Forecasting; Knowledge representation; Predictive analytics; Speech communication; Attention mechanisms; Causal convolutions; Convolutional networks; Financial indicator; Financial time series; Heterogeneous data sources; Heterogeneous sources; Inverse relationship; Motion estimation | Issue Date: | 2020 | Journal Volume: | 2020-May | Start page/Pages: | 8359-8363 | Source: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Abstract: | The purpose of this research is to develop a high performing model for stock movement prediction utilizing financial indicators and news data. Until recently, the majority of prediction models have employed only the financial indicators, but they possess the risk of missing unconventional agitators that can be derived from other heterogeneous sources. To address this, few research studies began to explore the use of news data and other social features along with financial indicators. In this work, we propose a novel integrative approach to effectively blend views from the news and financial time series. We generate event-knowledge representations from news data by capturing direct and inverse relationships among event tuples, and then apply attention mechanism to infer inter-day relationships among the representations. To capture temporal dynamics of financial indicators, we further integrate an attention augmented dilated causal convolutional network. We report empirically that our model achieves a substantial 5% improvement from 68.81% to 74.29% in stock movement prediction for the Standard Poor's 500 (SP500) index and companies over existing models. ? 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089220987&doi=10.1109%2fICASSP40776.2020.9053479&partnerID=40&md5=be614fd366a08c7921accf44efed397e https://scholars.lib.ntu.edu.tw/handle/123456789/580602 |
ISSN: | 15206149 | DOI: | 10.1109/ICASSP40776.2020.9053479 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.