A Trend-based Stock Index Forecasting Model with Gated Recurrent Neural Network

Liu, Yi-Jiao; Liu, Xinghua

doi:10.1109/pic.2018.8706267

Cited by 6 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al proposed a data preparation method based on mobile trend, and used the gating cycle unit (GRU) to model the stock index. The results show that the model has greatly improved the accuracy of stock index mobile trend prediction [12].…”

Section: Introductionmentioning

confidence: 93%

Research on Stock Trend Prediction Based on Improved LSTM Model

Zhang¹,

Tianhua²,

Zhang³

et al. 2022

Atlantis Highlights in Intelligent Systems

View full text Add to dashboard Cite

Aiming at the problem that deep features of stock data are difficult to extract and the prediction accuracy is not high, an improved LSTM model CGLA is constructed. Firstly, the RNN-Attention model, LSTM-Attention model and GRU-Attention model are constructed by using attention mechanism. GRU-Attention model with the best performance is selected by comparison. The deep features of stock time series data are extracted by CNN and sent to GRU-Attention model. Then LSTM is used to improve the network structure of the above training model, based on this, a hybrid CGLA model (CNN-GRU-LSTM-Attention) is constructed to predict the stock price of CSI300. After experimental verification, the MSE of CGLA model is reduced by two orders of magnitude compared with the comparison model, the R2_score is significantly improved, and the running time of CGLA model is greatly shortened compared with the comparison model. This paper also integrated factor correlation analysis, in a number of stock indicators in a comprehensive analysis of the closing price of the relevant stock indicators, combined with CGLA model to predict. The experimental results show that the combination of deep learning model and stock index influence factors can make the experiment obtain more accurate and more real stock trend prediction results.

show abstract

Section: Introductionmentioning

confidence: 93%

Research on Stock Trend Prediction Based on Improved LSTM Model

Zhang¹,

Tianhua²,

Zhang³

et al. 2022

Atlantis Highlights in Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…One is that existing studies only study pattern discovery of stock index instead of forming a complete structure and investigating pattern prediction further [25], [26], [27]. The second one is that these studies mainly focus on up-down prediction, while fail to recognize and predict various patterns of stock index further [28], [29]. The third one is that these researches mainly focus on pattern prediction of a single stock index without considering differences of various industries [19], [24].…”

Section: Literature Reviewmentioning

confidence: 99%

Discovery and Prediction of Stock Index Pattern via Three-Stage Architecture of TICC, TPA-LSTM and Multivariate LSTM-FCNs

Ouyang

Wei

2020

IEEE Access

View full text Add to dashboard Cite

In this study, we attempt to discover and predict stock index patterns through analysis of multivariate time series. Our motivation is based on the notion that financial planning guided by pattern discovery and prediction of stock index prices maybe more realistic and effective than traditional approaches, such as Autoregressive Integrated Moving Average (ARIMA) model. A three-stage architecture constructed by combining Toeplitz Inverse Covariance-Based Clustering (TICC), Temporal Pattern Attention and Long-Short-Term Memory (TPA-LSTM) and Multivariate LSTM-FCNs (MLSTM-FCN and MALSTM-FCN) is applied for pattern discovery and prediction of stock index. In the first stage, we use TICC to discover repeated patterns of stock index. Then, in the second stage, TPA-LSTM that considers weak periodic patterns and long short-term information is used to predict multivariate stock indices. Finally, in the third stage, MALSTM-FCN is applied to predict stock index price pattern. The Hangseng Stock Index and eleven industrial sub-indices are used in the experiment. Empirical results show that the three-stage architecture achieves satisfactory and better performance than traditional methods, such as Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), Random Forest (RF), etc. Moreover, we construct equal proportion portfolios based on the bullish trading rules to further analyze the feasibility of the proposed threestage architecture. Seven comprehensive stock indices are used in the experiment. Empirical results show that the portfolio based on the proposed three-stage architecture presents better performance than the marketbased portfolio. These findings may provide new direction for the portfolio construction and risk aversion. INDEX TERMS Stock index pattern, pattern discovery, pattern prediction, multivariate time series.

show abstract

“…Many real world problems can be formed in Multi-variate Time Series Forecasting (MTS) including traffic load forecasting [1,2], epidemic modeling [3], retail sales [4], finance [5], etc. that involve recorded temporal data from multiple sensors being processed and aligned into the same time axis.…”

Section: Introductionmentioning

confidence: 99%

“…Transformer-based approaches consist of spatial attention mechanism to discover the reciprocal salience of different spatial locations at each layer [8,9]. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) [2,10,11], have attracted an increasing attention because these methods not only archive outstanding performance on forecasting tasks but are also partially interpretable based on the graph structures, [12,13,14]. In general, STGNNs combine Graph Convolutional Networks (GCN) [15,16] to explore the relationship between time series and sequential models to capture the temporal dependencies.…”

Section: Introductionmentioning

confidence: 99%

Prospects of Blended Learning Implementation at FPT University Can Tho, Vietnam

Dao

Minh

Pham

et al. 2021

VJE

View full text Add to dashboard Cite

Drawing on the evaluations of students’ attitudes toward learning aspects the mixed-method research aims to examine the prospects of Blended Learning at FPT University in Can Tho. Four hundred sixty-seven students partook in the study by providing answers for a 30-item questionnaire with open-ended questions. The results showed that most students have positive attitudes towards factors constructing their Blended Learning adaptability, including (1) Study Management and Online Learning, (2) Classroom Learning, and (3) Learning Flexibility. The results of Binary Logistic Regression also clarified the good promise of Blended Learning implementation and the discovery of other concerns that hindered informants’ willingness, namely Worriment about Learning Effectiveness, Online Learning Barriers, and Learners’ Ego. The research findings served as a reference for FPT University and other higher institutions to better grasp how students perceive Blended Learning to develop strategies for successful practices.

show abstract

A Trend-based Stock Index Forecasting Model with Gated Recurrent Neural Network

Cited by 6 publications

References 8 publications

Research on Stock Trend Prediction Based on Improved LSTM Model

Research on Stock Trend Prediction Based on Improved LSTM Model

Discovery and Prediction of Stock Index Pattern via Three-Stage Architecture of TICC, TPA-LSTM and Multivariate LSTM-FCNs

Prospects of Blended Learning Implementation at FPT University Can Tho, Vietnam

Contact Info

Product

Resources

About