6,701 Hits in 6.7 sec

Stock Index Prices Prediction via Temporal Pattern Attention and Long-Short-Term Memory

Xiaolu Wei, Binbin Lei, Hongbing Ouyang, Qiufeng Wu, Constantine Kotropoulos
2020 Advances in Multimedia  
This study applied Temporal Pattern Attention and Long-Short-Term Memory (TPA-LSTM) for prediction to overcome the issue.  ...  The study's motivation is based on the notion that datasets of stock index prices involve weak periodic patterns, long-term and short-term information, for which traditional approaches and current neural  ...  In this study, we applied a different approach, Temporal Pattern Attention and Long Short-Term Memory (TPA-LSTM), to predict stock indexes' prices in different industries included in the Hangseng Composite  ... 
doi:10.1155/2020/8831893 fatcat:7xqotxxh4zaszkd5u2x42q6qgi

Discovery and Prediction of Stock Index Pattern via three-stage architecture of TICC, TPA-LSTM and Multivariate LSTM-FCNs (February 2019)

Hongbing Ouyang, Xiaolu Wei, Qiufeng Wu
2020 IEEE Access  
Temporal Pattern Attention and Long Short-Term Memory on Stock Index Prices Prediction TPA-LSTM was proposed by Shun-Yao Shih et al. in 2018 [6] , which was submitted to the journal track of European  ...  and Long-Short-Term Memory (TPA-LSTM) and Multivariate LSTM-FCNs (MLSTM-FCN, MALSTM-FCN), which are developed by David Hallac, D. et al  ... 
doi:10.1109/access.2020.3005994 fatcat:vja3zax7yfad7dhwcmhjgn3itm

Predicting Stock Closing Prices in Emerging Markets with Transformer Neural Networks: The Saudi Stock Exchange Case

Nadeem Malibari, Iyad Katib, Rashid Mehmood
2021 International Journal of Advanced Computer Science and Applications  
In our method, self-attention mechanisms are utilized to learn nonlinear patterns and dynamics from time-series data with high volatility and nonlinearity.  ...  The model makes predictions about closing prices for the next trading day by taking into account various stock price inputs.  ...  [17] , and the use of Long short-term memory network (LSTM) to predict the closing prices of iShares MSCI United Kingdom index [18] (for further motivation on the subject, see Section II).  ... 
doi:10.14569/ijacsa.2021.01212106 fatcat:fybiddl7mbbrpepvdqappauify

Forecasting Variation Trends of Stocks via Multiscale Feature Fusion and Long Short-Term Memory Learning

Yezhen Liu, Xilong Yu, Yanhua Wu, Shuhong Song, Chenxi Huang
2021 Scientific Programming  
While the Long Short-Term Memory (LSTM) network has the dedicated gate structure quite suitable for the prediction based on contextual features, we propose a novel LSTM-based model.  ...  The significance of our designed scheme is twofold. (1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively  ...  In addition, due to the difference between short and long terms, one fine-turning model probably works well in the short-term prediction, whereas could be poor in a longer time series.  ... 
doi:10.1155/2021/5113151 fatcat:7cuxdhd7lvbu7gw7xxc6px6i6a

Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport [article]

Hengxu Lin, Dong Zhou, Weiqing Liu, Jiang Bian
2021 arXiv   pre-print
In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns.  ...  Successful quantitative investment usually relies on precise predictions of the future movement of the stock price.  ...  In addition, we also evaluate the ranking performance of the learned model by constructing a long-short portfolio by longing stocks of the top decile and shorting stocks of the bottom decile 10 .  ... 
arXiv:2106.12950v2 fatcat:5o7tnlwapna2deknlaforvzvei

Stock Price Prediction Using Attention-based Multi-Input LSTM

Hao Li, Yanyan Shen, Yanmin Zhu
2018 Asian Conference on Machine Learning  
Stock price prediction has always been a hot but challenging task due to the complexity and randomness in stock market.  ...  We also introduce several new factors including the prices of other related stocks to improve the prediction accuracy.  ...  Long Short Term Memory (LSTM) model: The LSTM has been one of the most popular models for time series prediction in recent years.  ... 
dblp:conf/acml/LiSZ18 fatcat:h2ke45ouhvekbi3hh3qrg7mayy

Price graphs: Utilizing the structural information of financial time series for stock prediction [article]

Junran Wu, Ke Xu, Xueyuan Chen, Shangzhe Li, Jichang Zhao
2021 arXiv   pre-print
We take graph embeddings to represent the associations among temporal points as the prediction model inputs. Node weights are used as a priori knowledge to enhance the learning of temporal attention.  ...  Great research efforts have been devoted to exploiting deep neural networks in stock prediction.  ...  Based on "memory cells" that are designed to preserve information for a longer time, a special type of RNN, Long short-term memory (LSTM), has been developed and proven to be useful in predicting stock  ... 
arXiv:2106.02522v5 fatcat:deumr3gphfbpzebe47ftxa3nki

Deep Sequence Modeling: Development and Applications in Asset Pricing

Lin William Cong, Ke Tang, Jingyuan Wang, Yang Zhang
2020 The Journal of Financial Data Science  
We demonstrate how sequence modeling benefits investors in general through incorporating complex historical path dependence, and that Long- and Short-term Memory (LSTM) based models tend to have the best  ...  We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling.  ...  Acknowledgement: We are grateful to Frank Fabozzi, Andrew Karolyi, Andreas Neuhierl, Marcos de Prado, and Lu Zhang for their comments. We also thank Zihan Zhang for excellent research assistance.  ... 
doi:10.3905/jfds.2020.1.053 fatcat:dw5xmpxv7reb5em2rrpq4rjyfm

Forecasting Corporate Financial Time Series using Multi-phase Attention Recurrent Neural Networks

Shuhei Yoshimi, Koji Eguchi
2020 International Conference on Extending Database Technology  
This latest study achieved more effective prediction by employing attention structure that simultaneously capture the spatial relationships among multiple different time series and the temporal structure  ...  Moreover, such previous studies have not explored on financial time series incorporating macroeconomic time series, such as Gross Domestic Product (GDP) and stock market indexes, to our knowledge.  ...  ACKNOWLEDGMENTS We thank Takuji Kinkyo and Shigeyuki Hamori for valuable discussions and comments.  ... 
dblp:conf/edbt/YoshimiE20 fatcat:6npzv2jcyrbsffnyteixx7o2yq

MRC-LSTM: A Hybrid Approach of Multi-scale Residual CNN and LSTM to Predict Bitcoin Price [article]

Qiutong Guo and Shun Lei and Qing Ye and Zhiyang Fang
2021 arXiv   pre-print
In this paper, we propose a novel approach called MRC-LSTM, which combines a Multi-scale Residual Convolutional neural network (MRC) and a Long Short-Term Memory (LSTM) to implement Bitcoin closing price  ...  In the study, the impact of external factors such as macroeconomic variables and investor attention on the Bitcoin price is considered in addition to the trading information of the Bitcoin market.  ...  LSTM neural networks [14] have been shown to be significantly effective in forecasting bitcoin prices due to their ability to identify long-term dependencies and store both long-term and short-term temporal  ... 
arXiv:2105.00707v1 fatcat:4de4kxoshra2xp5vnxy4vwrlom

WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series

Michael Poli, Jinkyoo Park, Ilija Ilievski
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
of dissimilarity between the training and test periods in terms of volatility and general market regimes.  ...  Non-deliverable-forwards (NDF), a derivatives contract used in foreign exchange (FX) trading, presents additional difficulty in the form of long-term planning required for an effective selection of start  ...  MR believes that asset prices will eventually revert to the long-term mean.  ... 
doi:10.24963/ijcai.2020/623 dblp:conf/ijcai/LeeKYK20 fatcat:2pqk26wijfddblt5cpc5owz2d4

Stock Market Trend Prediction Using High-order Information of Time Series

Min Wen, Ping Li, Lingfei Zhang, Yan Chen
2019 IEEE Access  
INDEX TERMS Trend prediction, convolutional neural network, financial time series, motif extraction.  ...  In this paper, we introduced a new method to simplify noisy-filled financial temporal series via sequence reconstruction by leveraging motifs (frequent patterns), and then utilize a convolutional neural  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their constructive remarks and suggestions which helped us to improve the quality of the manuscript to a great extent.  ... 
doi:10.1109/access.2019.2901842 fatcat:rljx3ep5ljel5ccyxsseoj2kny

Managing Editor's Letter

Francesco A. Fabozzi
2021 The Journal of Financial Data Science  
They report that long short-term memory has the best performance in terms of out-of-sample predictive R-squared, and long short-term memory with an attention mechanism has the best portfolio performance  ...  Lin William Cong, Ke Tang, Jingyuan Wang, and Yang Zhang in their article "Deep Sequence Modeling: Development and Applications in Asset Pricing," show how to predict asset returns and measure risk premiums  ...  Here several deep learning techniques-H20 deep neural networks, a stacked autoencoder, long short-term memory, and the fusion of some of these techniques-are studied for estimating the equity premium (  ... 
doi:10.3905/jfds.2021.3.1.001 fatcat:rlm4fkjcjbd35bza3xvlj5lsay

Stock Price Movement Prediction Based on a Deep Factorization Machine and the Attention Mechanism

Xiaodong Zhang, Suhui Liu, Xin Zheng
2021 Mathematics  
In this paper, we constructed a convolutional neural network model based on a deep factorization machine and attention mechanism (FA-CNN) to improve the prediction accuracy of stock price movement via  ...  The prediction of stock price movement is a popular area of research in academic and industrial fields due to the dynamic, highly sensitive, nonlinear and chaotic nature of stock prices.  ...  Among DL models, the long-and short-term memory (LSTM) neural network dominates in the field of time series forecasting because of its unique algorithm mechanism [5, 6] .  ... 
doi:10.3390/math9080800 fatcat:lphqvfrzf5gyhdytupttbnxpdi

A Novel Bitcoin and Gold Prices Prediction Method Using an LSTM-P Neural Network Model

Xinchen Zhang, Linghao Zhang, Qincheng Zhou, Xu Jin, Shengrong Gong
2022 Computational Intelligence and Neuroscience  
Third, in the price prediction model, we develop an optimized LSTM prediction model (LSPM-P) and train it using historical price data for gold and Bitcoin to make accurate predictions.  ...  In addition, our LSTM-P model outperforms both the conventional LSTM models and other time series forecasting models in terms of accuracy and precision.  ...  In order to forecast the stock prices of selected companies, a long short-term memory model is utilized to analyze the daily stock price movement and returns of different sectors based on their prior values  ... 
doi:10.1155/2022/1643413 pmid:35571687 pmcid:PMC9098287 fatcat:pg6ecx2gzvg2nh2rv4in3nds6e
« Previous Showing results 1 — 15 out of 6,701 results