Knowledge-driven stock trend prediction and explanation via temporal convolutional network

Shumin Deng, Ningyu Zhang, Wen Zhang, Jiaoyan Chen, Jeff Z. Pan, Huajun Chen

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

99 Citations (Scopus)
18 Downloads (Pure)

Abstract

Deep neural networks have achieved promising results in stock trend prediction. However, most of these models have two common drawbacks, including (i) current methods are not sensitive enough to abrupt changes of stock trend, and (ii) forecasting results are not interpretable for humans. To address these two problems, we propose a novel Knowledge-Driven Temporal Convolutional Network (KDTCN) for stock trend prediction and explanation. Firstly, we extract structured events from financial news, and utilize external knowledge from knowledge graph to obtain event embeddings. Then, we combine event embeddings and price values together to forecast stock trend. We evaluate the prediction accuracy to show how knowledge-driven events work on abrupt changes. We also visualize the effect of events and linkage among events based on knowledge graph, to explain why knowledge-driven events are common sources of abrupt changes. Experiments demonstrate that KDTCN can (i) react to abrupt changes much faster and outperform state-of-the-art methods on stock datasets, as well as (ii) facilitate the explanation of prediction particularly with abrupt changes.

Original languageEnglish
Title of host publicationCompanion Proceedings of the 2019 World Wide Web Conference (WWW ’19 Companion)
EditorsLing Liu, Ryen White
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages678-685
Number of pages8
ISBN (Electronic)9781450366755
DOIs
Publication statusPublished - 13 May 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: 13 May 201917 May 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
Country/TerritoryUnited States
CitySan Francisco
Period13/05/1917/05/19

Bibliographical note

The authors would like to acknowledge that this work is funded by NSFC 61473260/91846204, national key research program YS2018YFB140004 as well as Natural Science Foundation of Zhejiang Province of China (LQ19F030001), and supported by Alibaba-Zhejiang University Joint Institute of Frontier Technologies.

Keywords

  • Event extraction
  • Explanation
  • Knowledge-driven
  • Predictive analytics
  • Stock trend prediction
  • Structured
  • Unstructured
  • REPRESENTATIONS
  • predictive analytics
  • stock trend prediction
  • explanation
  • event extraction
  • unstructured
  • structured

Fingerprint

Dive into the research topics of 'Knowledge-driven stock trend prediction and explanation via temporal convolutional network'. Together they form a unique fingerprint.

Cite this