Forecasting movements of stock time series based on hidden state guided deep learning approach

Jiang, Junji; Wu, Likang; Zhao, Hongke; Zhu, Hengshu; Zhang, Wei

doi:10.1016/j.ipm.2023.103328

Cited by 16 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, various deep learning techniques, including MLP, CNN, LSTM, and CNN-LSTM combinations, have been employed for time series prediction [13], [29]. These methods excel in capturing complex time-dependent relationships, as highlighted in Table 1.…”

Section: Related Workmentioning

confidence: 99%

“…The mentioned table demonstrates LSTM's efficacy in predicting student performance by surpassing baseline models, such as SVM and MLP, with superior accuracy [30]. LSTM's adeptness in handling sequential data and retaining long-term information enhances its adaptability to the complexities of educational data, resulting in enhanced predictions [29]. In contrast to alternatives, LSTM offers reliable and precise predictions, making it the preferred model for educational grade prediction [18].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Course Grades in Computer Science Higher Education Program via a Combination of Loss Functions in LSTM Model

Ghazvini,

Mohd Sharef,

Sidi

2024

IEEE Access

View full text Add to dashboard Cite

In the domain of education, timely intervention through early prediction of student grades holds critical significance. This is due to challenges such as learning difficulties, exemplified by the prevention of dropout, and the facilitation of individualized learning. To address these issues, nonlinear dynamic systems, notably Recurrent Neural Networks (RNNs), have demonstrated efficacy in unraveling the intricate relationships within student performance data, surpassing the constraints of traditional time series methods. However, the challenge of vanishing gradient issues hampers RNNs, leading to a significant decrease in gradient values during weight matrix multiplication. To solve this challenge, we introduce an innovative loss function, the MSECosine loss function crafted by seamlessly combining two established loss functions: Mean Square Error (MSE) and LogCosh. The incorporation of logarithmic terms in the MSE function mitigates error escalation, countering its tendency to amplify errors through square terms. The primary focus of this study is to propose and demonstrate the efficacy of the MSECosine loss function. In assessing the performance of this novel loss function, we employed two selfcollected datasets comprising learning management system (LMS) and assessment records. These datasets serve as the testing ground for four deep time series models: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory network (LSTM), and CNN-LSTM. Employing 29 meticulously designed feature selection models, LSTM emerges as the preeminent model. Building on this groundwork, we boost the LSTM model's performance by integrating the proposed MSECosine loss function, resulting in an enhanced model termed eLSTM. Experimental results underscore the noteworthy achievements of the eLSTM model, emphasizing an accuracy of 0.6191% and a substantially reduced error rate of 0.1738. These outcomes surpass those of alternative approaches, highlighting the instrumental role of the MSECosine loss function in refining eLSTM for more accurate predictions in early student grade forecasting.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Prediction of Course Grades in Computer Science Higher Education Program via a Combination of Loss Functions in LSTM Model

Ghazvini,

Mohd Sharef,

Sidi

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…By contrast, machine learning methods can model nonlinearities (J. Jiang et al, 2023), and the forecasting accuracy is usually superior to statistical methods (Huang et al, 2021). The commonly used machine learning techniques are BP and SVR.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced IHHO-LSTM Model for Predicting Online Public Opinion Trends in Public Health Emergencies

Mu,

Li,

Liao

et al. 2024

Sage Open

View full text Add to dashboard Cite

Social networks accelerate information communication in public health emergencies. Some negative information may cause an outbreak of public opinion crisis. Accurately predicting online public opinion trends can help the relevant departments take timely and effective measures to cope with risks. Therefore, this research proposes a prediction model incorporating the swarm intelligence optimization algorithm and the deep learning method. In this model, we improve the Harris Hawks Optimization (HHO) algorithm by introducing the Cauchy distribution function, the stochastic contraction exponential function, and the adaptive inertia weight. Then we utilize the improved HHO (IHHO) algorithm to optimize the hyperparameters of the deep learning method LSTM, including the learning rate and the number of neurons in the hidden layer. Finally, we construct the IHHO-LSTM model to make predictions in three public health emergencies. The experiments verify that the proposed model outperforms other single and hybrid models. The MAPE values reduce by 78.34%, 54.46%, and 46.42% relative to the average values of the three single models. Compared with the mean values of the two hybrid models, the MAPE values decrease by 47.69%, 18.45%, and 5.78%. The IHHO-LSTM model can be applied to public opinion early warning and reversal identification, providing a reference in public opinion management.

show abstract

“…Typical methods include autoregressive moving average, autoregressive integrated moving average, and generalized autoregressive conditional heteroskedasticity models (Zhang, Li, et al, 2023;Yin et al, 2023;Sonkavde et al, 2023). However, the nonstationarity, nonlinearity, and other characteristics of stock prices result in significant limitations of traditional methods in stock trend prediction (Kurani et al, 2023;Dezhkam & Manzuri, 2023;Jiang et al, 2023;Amin et al, 2024).…”

Section: Introductionmentioning

confidence: 99%

Predicting Stock Trends Using Web Semantics and Feature Fusion

Zhou,

Jumahong,

Cui

et al. 2024

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Stock data are characterized by high dimensionality and sparsity, making stock trend prediction highly challenging. Although the LightGBM(Light Gradient Boosting Machine), based on web semantics, excels at capturing global features and efficiently performs in stock trend prediction, it does not consider the issue of declining prediction performance caused by the changing distribution of stock data over time (concept drift phenomenon). Accordingly, this work introduces the CNN (Convolutional Neural Network) into the prediction model to leverage its ability to effectively capture local features. Additionally, local features are combined with global features to obtain a comprehensive set of feature information. Lastly, the model processes new data in real-time, continuously learns new knowledge, updates model parameters, and effectively addresses the decline in model performance caused by concept drift. Experimental results demonstrate that the proposed model outperforms other models indicating its ability to efficiently perform well in stock trend prediction.

show abstract

Forecasting movements of stock time series based on hidden state guided deep learning approach

Cited by 16 publications

References 38 publications

Prediction of Course Grades in Computer Science Higher Education Program via a Combination of Loss Functions in LSTM Model

Prediction of Course Grades in Computer Science Higher Education Program via a Combination of Loss Functions in LSTM Model

An Enhanced IHHO-LSTM Model for Predicting Online Public Opinion Trends in Public Health Emergencies

Predicting Stock Trends Using Web Semantics and Feature Fusion

Contact Info

Product

Resources

About