4.7 Article

Attentive gated graph sequence neural network-based time-series information fusion for financial trading

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Sentiment-influenced trading system based on multimodal deep reinforcement learning

Yu-Fu Chen et al.

Summary: This study introduces a multimodal reinforcement trading system that utilizes reinforcement learning, sentiment analysis, and multimodal learning techniques to improve performance. Experimental results show that multimodal agents outperform price-concerned agents by at least 13.26%. The proposed influence model has the ability to shape the impact of news on the stock market, aiding the multimodal agents in evaluating the market status effectively.

APPLIED SOFT COMPUTING (2021)

Article Computer Science, Artificial Intelligence

Multi-source information fusion and deep-learning-based characteristics measurement for exploring the effects of peer engagement on stock price synchronicity

Lin Li et al.

Summary: By combining financial information with social textual information, this study examines the effects of peer engagement on stock price synchronicity. It finds that peer engagement reduces synchronicity, especially during epidemics, where group diversity and experts play a stronger role in lowering synchronicity.

INFORMATION FUSION (2021)

Article Computer Science, Artificial Intelligence

DeepOption: A novel option pricing framework based on deep learning with fused distilled data from multiple parametric methods

Ji Hyun Jang et al.

Summary: The study introduces a new deep learning framework called DeepOption, which can improve performance on imbalanced real option data. The framework combines simulated big data and real data, utilizing a three-stage training approach. Experimental results show that the framework outperforms traditional parametric methods and other machine learning methods.

INFORMATION FUSION (2021)

Article Computer Science, Information Systems

Novel Deep Reinforcement Algorithm With Adaptive Sampling Strategy for Continuous Portfolio Optimization

Szu-Hao Huang et al.

Summary: This study discusses the application of artificial intelligence in quantitative trading and proposes an RL portfolio management method that combines adversarial learning and a novel sampling strategy to obtain reliable trading rules.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Interpretable Stock Anomaly Detection Based on Spatio-Temporal Relation Networks With Genetic Algorithm

Mei-See Cheong et al.

Summary: The study proposed a model to help investors detect financial market anomalies early, and utilize an interpretable model to explain these anomalies, helping investors have a comprehensive understanding of the stock market situation.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Deep Learning Model for House Price Prediction Using Heterogeneous Data Analysis Along With Joint Self-Attention Mechanism

Pei-Ying Wang et al.

Summary: This study proposes an end-to-end joint self-attention model for house price prediction, which incorporates various factors affecting house prices, including public facility data and satellite maps. By utilizing attention mechanisms to identify crucial features, the model outperforms other machine learning-based models and achieves low prediction error in experiments.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy

Yu-Ying Chen et al.

Summary: This study investigates the combination of deep neural networks and reinforcement learning in automatic trading systems, introducing an enhanced version of the ensemble of identical independent evaluators method to counter malicious adversarial attacks. Results show that the enhanced EIIE method is over 30% more effective in reducing accumulated portfolio value compared to traditional attack mechanisms.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Improving Generalization in Reinforcement Learning-Based Trading by Using a Generative Adversarial Market Model

Chia-Hsuan Kuo et al.

Summary: Reinforcement learning has been widely used in portfolio management, but issues like ignoring market impact and causal relationships within interaction processes exist. By introducing a generative model to simulate the financial market and constructing a virtual market as an interactive training environment, better generalizations can be achieved for RL-based portfolio agents.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

M-GCN: Multi-Branch Graph Convolution Network for 2D Image-based on 3D Model Retrieval

Wei-Zhi Nie et al.

Summary: The study introduces a novel approach for 3D model retrieval based on 2D images, utilizing a multi-branch graph convolution network and a multi-head attention mechanism to enhance the relationship between nodes and improve retrieval performance.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Article Computer Science, Artificial Intelligence

Portfolio management via two-stage deep learning with a joint cost

Hyungbin Yun et al.

EXPERT SYSTEMS WITH APPLICATIONS (2020)

Article Computer Science, Artificial Intelligence

A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction

Sicen Liu et al.

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2020)

Article Computer Science, Artificial Intelligence

Learning heterogeneous information network embeddings via relational triplet network

Xiyue Gao et al.

NEUROCOMPUTING (2020)

Article Engineering, Civil

Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

Zhiyong Cui et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Lagged correlation-based deep learning for directional trend change prediction in financial time series

Ben Moews et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Article Computer Science, Artificial Intelligence

Deep learning for decision making and the optimization of socially responsible investments and portfolio

Nhi N. Y. Vo et al.

DECISION SUPPORT SYSTEMS (2019)

Article Computer Science, Artificial Intelligence

Time series forecasting of petroleum production using deep LSTM recurrent networks

Alaa Sagheer et al.

NEUROCOMPUTING (2019)

Article Management

Deep learning with long short-term memory networks for financial market predictions

Thomas Fischer et al.

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH (2018)

Article Business, Finance

WHOM YOU CONNECT WITH MATTERS: DIRECTOR NETWORKS AND FIRM LOCATION

Lindsay Baran et al.

JOURNAL OF FINANCIAL RESEARCH (2018)

Article Business, Finance

A five-factor asset pricing model

Eugene F. Fama et al.

JOURNAL OF FINANCIAL ECONOMICS (2015)

Article Computer Science, Artificial Intelligence

The Graph Neural Network Model

Franco Scarselli et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2009)

Article Economics

Where do manufacturing firms locate their headquarters?

J. Vernon Henderson et al.

JOURNAL OF URBAN ECONOMICS (2008)

Article Statistics & Probability

Structural learning with time-varying components: tracking the cross-section of financial time series

M Talih et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2005)

Article Computer Science, Artificial Intelligence

Financial time series forecasting using support vector machines

KJ Kim

NEUROCOMPUTING (2003)

Article Automation & Control Systems

Variable grouping in multivariate time series via correlation

A Tucker et al.

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS (2001)

Article Statistics & Probability

Graphical interaction models for multivariate time series

R Dahlhaus

METRIKA (2000)