Article
Computer Science, Artificial Intelligence
Hadi Rezaei, Hamidreza Faaljou, Gholamreza Mansourfar
Summary: The combination of new deep learning and decomposition algorithms has improved the accuracy and performance of financial time series analysis. Combining CEEMD with CNN and LSTM can produce better prediction results.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Hardware & Architecture
Liwei Tian, Li Feng, Lei Yang, Yuankai Guo
Summary: The paper introduces a hybrid model named LSTM-BO-LightGBM based on LSTM and LightGBM for stock price fluctuation prediction, which demonstrates better prediction accuracy and generalization ability compared to other models.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Shengting Wu, Yuling Liu, Ziran Zou, Tien-Hsiung Weng
Summary: This paper proposes a stock price prediction method S_I_LSTM that combines multiple data sources and investor sentiment using sentiment analysis and convolutional neural network, as well as long short-term memory network for predicting the China Shanghai A-share market. Experimental results show that the method outperforms traditional methods on real data sets of five listed companies.
CONNECTION SCIENCE
(2022)
Article
Computer Science, Information Systems
Zhongtian Ji, Peng Wu, Chen Ling, Peng Zhu
Summary: In this paper, a stock price prediction model based on attention-based Long Short Term Memory (ALSTM) network is established, utilizing price data, technical indicators, and sentiment information from social media. Experimental results indicate that the proposed method outperforms baseline models in terms of mean absolute error, root mean square error, and accuracy. Models incorporating stock prices, technical indicators, and sentiment features perform better than models using partial data sources. The fine-tuned BERT model performs better in sentiment classification task and exploiting sentiment features computed with BERT model leads to higher predicting accuracy compared to the features calculated using sentiment lexicon. Setting the input window length to 5-day achieves the best performance in average prediction accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Mathematics
Jilin Zhang, Lishi Ye, Yongzeng Lai
Summary: Accurate prediction of stock prices is crucial in stock investment, but it is challenging due to the characteristics of high frequency, nonlinearity, and long memory in stock price data. This paper proposes a CNN-BiLSTM-Attention-based model, which extracts temporal features using CNN and BiLSTM, incorporates attention mechanism to assign weights automatically, and outputs final prediction results through dense layer. Experimental results show that the proposed model outperforms LSTM, CNN-LSTM, and CNN-LSTM-Attention models in predicting Chinese stock index (CSI300) price, and it also demonstrates robust effectiveness in predicting other Chinese and international stock indices.
Article
Computer Science, Artificial Intelligence
Yang Yujun, Yang Yimei, Zhou Wang
Summary: The study proposes a hybrid prediction model based on LSTM and VMD for forecasting stock prices. By decomposing the stock price time series into stable subsequences, training and predicting, the model demonstrates high prediction accuracy. The experimental results show an accuracy of over 0.991 on each dataset, making it an effective tool for stock market prediction.
Article
Computer Science, Artificial Intelligence
Anika Kanwal, Man Fai Lau, Sebastian P. H. Ng, Kwan Yong Sim, Siva Chandrasekaran
Summary: This research proposes a hybrid deep learning-based predictive model for timely and efficient prediction of stock prices. The model combines a Bidirectional Cuda Deep Neural Network Long Short-Term Memory and a one-dimensional Convolutional Neural Network, and has shown accurate prediction results for supporting informed investment decisions.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Gourav Bathla, Rinkle Rani, Himanshu Aggarwal
Summary: This study investigates the possibility of using deep learning to predict high variations in stock prices in 2020 and proposes a corresponding neural network model. The experimental analysis demonstrates that the LSTM model, with the set up used in this study, is able to predict stock prices with sufficient accuracy, with MAPE values better than traditional data analytics techniques.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Huiru Li, Yanrong Hu, Hongjiu Liu
Summary: This paper proposes a novel LASSO-ATT-LSTM intelligent stock price prediction system based on multi-source data, considering the influence of unstructured data such as investor sentiment on stock price volatility. The system utilizes a sentiment dictionary in the financial field to analyze news information and comments, calculates sentiment scores, and obtains daily investor sentiment. The LASSO method is used to reduce the dimension of trading indicators, valuation indicators, and technical indicators, and the processed indicators and investor sentiment are inputted into the prediction model. The LSTM model with attention mechanism is used for intelligent prediction. The results show that the proposed model has high accuracy and is an effective method for stock price prediction, with MAPE, RMSE, MAE, and R-2 values of 0.0118, 0.0685, 0.0515, and 0.8460, respectively.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Burak Gulmez
Summary: The stock market is a financial market where shares of publicly listed corporations are bought and sold, and it reflects a country's economic health. Investing in stocks carries risks, but it has the potential for significant long-term returns. Artificial intelligence, including the stock market, is increasingly prevalent in the financial sector.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Shilpa Gite, Hrituja Khatavkar, Ketan Kotecha, Shilpi Srivastava, Priyam Maheshwari, Neerav Pandey
Summary: The stock market is influenced by complex sentiments and media releases, making price predictions challenging. This paper proposes using machine learning and LSTM to improve accuracy by incorporating sentiment analysis. LSTM has proven effective in learning long-term dependencies, and when combined with historical stock data and news sentiment, it can enhance predictive models.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Yufeng Chen, Jinwang Wu, Zhongrui Wu
Summary: This study proposes a novel hybrid deep learning approach that utilizes an improved clustering algorithm and LSTM neural network model to predict stock prices more accurately. Experimental results demonstrate that this method outperforms traditional statistical models in terms of prediction ability and accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Mathematics
Xiaodong Zhang, Suhui Liu, Xin Zheng
Summary: The study proposed a FA-CNN model for predicting stock price movement by enhancing feature learning. Experimental results demonstrated that the model achieved good performance in extracting intraday interactions and utilizing sub-industry index information as additional input features.
Article
Computer Science, Artificial Intelligence
Xiao Teng, Xiang Zhang, Zhigang Luo
Summary: This paper proposes a multi-scale local cues and hierarchical attention-based LSTM model for stock price trend prediction. Experiments confirm the superior performance of the proposed model compared to existing models.
Article
Computer Science, Information Systems
Guangyu Mu, Nan Gao, Yuhan Wang, Li Dai
Summary: This paper combines multi-source data, sentiment analysis, swarm intelligence algorithm, and deep learning to build the MS-SSA-LSTM model for predicting stock prices. The experiments demonstrate that the model outperforms others and has high universal applicability.