Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network

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

doi:10.1145/3308560.3317701

Cited by 135 publications

(63 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the data set is divided into the same proportions as our model in these baselines, and also the optimization process (grid search). Since Deng et al [32] introduced the knowledge graph in their model, and we do not draw on any knowledge, so we do not compare with their model and other models using knowledge. Details of the baselines are described below:…”

Section: Comparison Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Element Hierarchical Attention Capsule Network for Stock Prediction

et al. 2020

View full text Add to dashboard Cite

Stock prediction is a challenging task concerned by researchers due to its considerable returns. It is difficult because of the high randomness in the stock market. Stock price movement is mainly related to the capital situation and hot events. In recent years, researchers improved prediction accuracy with news and social media. However, the existing methods do not take into account the different influences of events. To solve this problem, we propose a multi-element hierarchical attention capsule network, which consists of two components. The former component, multi-element hierarchical attention, quantifies the importance of valuable information contained in multiple news and social media through its weights assignment process. And the latter component, capsule network, learns more context information from the events through its vector representation in the hidden layer. Moreover, we construct a combined data set to maintain the complementarity between social media and news. Finally, we achieve better results than baselines, and experiments show that our model improves prediction accuracy by quantifying the different influences of events.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

“…Therefore, different from other classification tasks, a text data of a stock is equivalent to a data set in the stock prediction task. For these reasons, inspired by Xu et al [18], Hu et al [31], and Deng et al [32], we adopt one data set to verify our model as the following methods.…”

Section: Experiments a Datasetmentioning

confidence: 99%

Multi-Element Hierarchical Attention Capsule Network for Stock Prediction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…along with knowledge graph embeddings through TransR. However, such existing approaches (Deng et al, 2019) are unable to represent textual signals from social media and prices temporally, as they only utilize sentiment scores and do not account for stock correlations. To cover this gap in prior research, MAN-SF captures a broader set of features as opposed to both conventional TA and FA that singularly focus on either text or graph modalities, but not both together.…”

Section: Related Workmentioning

confidence: 99%

Deep Attentive Learning for Stock Movement Prediction From Social Media Text and Company Correlations

Sawhney

Agarwal²,

Wadhwa

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

In the financial domain, risk modeling and profit generation heavily rely on the sophisticated and intricate stock movement prediction task. Stock forecasting is complex, given the stochastic dynamics and non-stationary behavior of the market. Stock movements are influenced by varied factors beyond the conventionally studied historical prices, such as social media and correlations among stocks. The rising ubiquity of online content and knowledge mandates an exploration of models that factor in such multimodal signals for accurate stock forecasting. We introduce an architecture that achieves a potent blend of chaotic temporal signals from financial data, social media, and inter-stock relationships via a graph neural network in a hierarchical temporal fashion. Through experiments on real-world S&P 500 index data and English tweets, we show the practical applicability of our model as a tool for investment decision making and trading.

show abstract

“…But they should extend their work for financial domain related knowledge graph. Deng et al (2019) employed the similar technique for event embedding using knowledge graph to refine event embedding. For prediction, Temporal Convolutional Network (TCN) is employed that outperformed other deep learning models especially for abrupt changes of stock trend.…”

Section: Literature Reviewmentioning

confidence: 99%

News sensitive stock market prediction: literature review and suggestions

Usmani¹,

Shamsi²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Stock market prediction is a challenging task as it requires deep insights for extraction of news events, analysis of historic data, and impact of news events on stock price trends. The challenge is further exacerbated due to the high volatility of stock price trends. However, a detailed overview that discusses the overall context of stock prediction is elusive in literature. To address this research gap, this paper presents a detailed survey. All key terms and phases of generic stock prediction methodology along with challenges, are described. A detailed literature review that covers data preprocessing techniques, feature extraction techniques, prediction techniques, and future directions is presented for news sensitive stock prediction. This work investigates the significance of using structured text features rather than unstructured and shallow text features. It also discusses the use of opinion extraction techniques. In addition, it emphasizes the use of domain knowledge with both approaches of textual feature extraction. Furthermore, it highlights the significance of deep neural network based prediction techniques to capture the hidden relationship between textual and numerical data. This survey is significant and novel as it elaborates a comprehensive framework for stock market prediction and highlights the strengths and weaknesses of existing approaches. It presents a wide range of open issues and research directions that are beneficial for the research community.

show abstract

Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network

Cited by 135 publications

References 35 publications

Multi-Element Hierarchical Attention Capsule Network for Stock Prediction

Multi-Element Hierarchical Attention Capsule Network for Stock Prediction

Deep Attentive Learning for Stock Movement Prediction From Social Media Text and Company Correlations

News sensitive stock market prediction: literature review and suggestions

Contact Info

Product

Resources

About