Research on the Feasibility of Applying GRU and Attention Mechanism Combined with Technical Indicators in Stock Trading Strategies

Lee, Ming-Che

doi:10.3390/app12031007

Cited by 22 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ChwðCþ K 2 ÞÞ. Since the input to the GRU is a sequence of m frames representing a given video, the time complexity of a single GRU is Oðmd 2 h þ md h d i Þ where d h and d i represent dimensions of hidden state and input, respectively [71,72]. The GRUs sequence has a time complexity…”

Section: Time Complexity Analysis Of the Proposed Methodsmentioning

confidence: 99%

An integrated spatiotemporal-based methodology for deepfake detection

Ismail

Elpeltagy

Zaki

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Rapid advances in deep learning models have made it easier for public and crackers to generate hyper-realistic deepfake videos in which faces are swapped. Such deepfake videos may constitute a significant threat to the world if they are misused to blackmail public figures and to deceive systems of face recognition. As a result, distinguishing these fake videos from real ones has become fundamental. This paper introduces a new deepfake video detection method. You Only Look Once (YOLO) face detector is used to detect faces from video frames. A proposed hybrid method based on proposing two different feature extraction methods is applied to these faces. The first feature extraction method, a proposed Convolution Neural Network (CNN), is based on the Histogram of Oriented Gradient (HOG) method. The second one is an ameliorated XceptionNet CNN. The two extracted sets of features are merged together and fed as input to a sequence of Gated Recurrent Units (GRUs) to extract the spatial and temporal features and then individuate the authenticity of videos. The proposed method is trained on the CelebDF-FaceForencics++ (c23) dataset and evaluated on the CelebDF test set. The experimental results and analysis confirm the superiority of the suggested method over the state-of-the-art methods.

show abstract

Section: Time Complexity Analysis Of the Proposed Methodsmentioning

confidence: 99%

An integrated spatiotemporal-based methodology for deepfake detection

Ismail

Elpeltagy

Zaki

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…It is designed to capture long-range dependencies and patterns in sequences, making it suitable for tasks like stock forecasting. GRU was specifically designed as a way to address some of the limitations of traditional RNNs, such as the vanishing gradient problem [18] [19]. GRU has a more simple architecture than LSTM, and is equally as viable when it comes to being used for stock predictions.…”

Section: Grumentioning

confidence: 99%

“…GRU has a more simple architecture than LSTM, and is equally as viable when it comes to being used for stock predictions. This is due to the fact that it is capable of yielding strong results [18] as well as outperforming other high-achieving models [19]. This is, in part, due to its fast training speed and efficiency at capturing short-term dependencies within sequences.…”

Section: Grumentioning

confidence: 99%

Literature Review: Machine Learning in Stock Predictions

2024

HBEM

View full text Add to dashboard Cite

Machine learning has revolutionized the field of stock prediction by offering a wide range of models capable of handling complex patterns and making accurate forecasts. Machine learning models vary widely in their application, uses, and effectiveness, and stocks vary as well in terms of volatility within the stock and also between stocks of different industries and at different market conditions. As such, the selection of the proper algorithmic tool to aid an investor is often difficult. This literature review paper provides an overview of ten popular machine learning models over two problem types (prediction and classification), namely Linear Regression, XGBoost, LSTM, ARIMA, GARCH, Random Forest, Logistic Regression, Adaboost, GRU, and CNN. By providing an exploration of these ten machine learning models, this literature review offers valuable insights into their underlying principles, applications and uses, results strengths, and limitations. This paper equally, by consequent, facilitates informed decision-making and encourages further research in the field of machine learning.

show abstract

“…The Informer algorithm uses the ProbSparse Self-attention mechanism in the process of encoding and decoding, and only considers the part that contributes the most to the attention mechanism. Compared with LSTM [11] and Transformer [12], the calculation amount is smaller and the memory usage is low.…”

Section: Informer Model For Long-term Stock Price Predictionmentioning

confidence: 99%

Long-term stock price forecast based on PSO-informer model

Liu

Deng²,

Wei³

et al. 2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

The long-term prediction of stock prices provides an important reference for quantitative investment decisions. Aiming at the problem of insufficient accuracy of long-term series prediction in existing stock forecasting models, this paper proposes a long-term stock price series forecasting method based on PSO-Informer. First, 43 kinds of technical indicator factors and K-line data were selected to construct the input data, and then the PSO-Informer model was used to predict the future 60 time points of the stock closing price. In the model training process, the particle swarm algorithm is used to optimize the parameters of the Informer network. Based on the five-minute K-line data of the SSE 50 stock index and the CSI 300 stock index, experimental research was conducted respectively. Taking the accuracy of the long-term stock price prediction overall trend as the evaluation index, and the prediction accuracy reaches 68.2% and 67.5% respectively. The comparison experiments with ARIMA, Prophet, PSO-LSTM and Informer prediction models show that the model has the best performance and is practical.

show abstract

Research on the Feasibility of Applying GRU and Attention Mechanism Combined with Technical Indicators in Stock Trading Strategies

Cited by 22 publications

References 36 publications

An integrated spatiotemporal-based methodology for deepfake detection

An integrated spatiotemporal-based methodology for deepfake detection

Literature Review: Machine Learning in Stock Predictions

Long-term stock price forecast based on PSO-informer model

Contact Info

Product

Resources

About