Multi-source aggregated classification for stock price movement prediction

Ma, Yu; Mao, Rui; Lin, Qika; Wu, Peng; Wang, Zhaoxia

doi:10.1016/j.inffus.2022.10.025

Cited by 61 publications

(18 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A four-recurrent-layer, 50-neuron model was trained. 60-time steps 1 Indicator of dependency target variable on independent variables 2 Indicator of dependency target variable on independent variables after train-test split 3 Indicator of model evaluation to predict stock price on subsequent day Fig. 6 Reliance Industry stock's 30th day adjusted close price direction and 1-dimensionality characterized the input data.…”

Section: Resultsmentioning

confidence: 99%

“…Thus, using the information source makes sentiment analysis for stock prediction easier. Text mining allows researchers to compile textual information gleaned from online sources such as online media, and internet searches [3] and pre-trained models on massive data-set. Investor sentiment affects the stock market.…”

Section: The Use Of Sentiment Analysis In the Prediction Of Stock Mar...mentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach of Stock Price Direction and Price Prediction Based on News Sentiments

Singh,

Malhotra

2023

Preprint

View full text Add to dashboard Cite

Forecasting stock trends guide investment management, financial policy, and the country’s economic growth. Investor-generated textual information has impacted stock movements across media channels in recent years. Most sentiment index studies weigh linguistic content equally. Such studies ignore that the sentiment index’s impact on the stock market decreases over time. This study analyses stock indices using dual classifier coupling and sentiment analysis. A dual classifier is created by combining two popular classifiers, Decision Tree (DT) with Convolution Bi-Directional Gated Recurrent Unit (GRU). The proposed model is tested using Reliance Industries shares. The adjusted sentiment index improved overall accuracy in the Reliance Industries stock news sentiment analysis case study by 84.12 percent. The investor sentiment indicator improves stock index trend prediction, as shown by a 3.16 RMSE (Root Mean Squared Error) and 0.97 R2(Coefficient of determination) reduction. The adjusted sentiment index improves predicted accuracy considerably. The investors’ sentiments improve the overall results in Reliance Industries’ stock price prediction with our fusion of pro- posed VADER (Valence Aware Dictionary and sEntiment Reasoner) and CNN + BDGRU models compared to benchmark models.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: The Use Of Sentiment Analysis In the Prediction Of Stock Mar...mentioning

confidence: 99%

A Novel Approach of Stock Price Direction and Price Prediction Based on News Sentiments

Singh,

Malhotra

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Linguistic metaphor identification has been widely studied with the help of two shared tasks (Leong et al, 2018(Leong et al, , 2020 and the large-scale annotated VUA dataset (Steen et al, 2010b). Scholars have also noticed the connection between linguistic metaphor processing and other tasks, such as affective computing (Xing et al, 2020;Duong et al, 2022;Mao et al, 2022b;Cambria et al, 2022a;Ma et al, 2023). However, there are sub-types of linguistic metaphors that have not been well studied yet, such as extended metaphors and metaphoric MWEs.…”

Section: Discussionmentioning

confidence: 99%

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Mao

Cambria

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Metaphor is a figurative language that has been frequently used in our daily lives. Due to its significance for downstream natural language processing tasks, such as machine translation and sentiment analysis, computational metaphor processing has set off an upsurge in the community. With the development of Artificial Intelligence, an increasing number of technological tools and frameworks have been proposed in this domain. In this article, we aim to comprehensively summarize and categorize previous computational metaphor processing approaches regarding metaphor identification, interpretation, generation, and application. Meanwhile, we compare the strengths and weaknesses of current works and conceive future directions in this field.

show abstract

“…Wei-Chao Lin et al [28] utilized text mining techniques (using word2vec + CNN or Bert + CNN) to achieve the best performance in stock price trend prediction experiments. Yu Ma et al [29] introduced a new Multi-Source Aggregation Classification (MAC) method to predict stock price trends, also relying on convolutional neural network models in deep learning. Dezfouli P A B et al [4] trained a model in the hidden layers using a network structure combining only CNN and Max Pooling, which outperformed baseline models like DeepCoNN [30], TransNets [31], TransNet-Ext [31] based on neural networks.…”

Section: Text Feature Extractionmentioning

confidence: 99%

Hourglass pattern matching for deep aware neural network text recommendation model

Gao,

Li,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

In recent years, with the rapid development of deep learning, big data mining, and natural language processing (NLP) technologies, the application of NLP in the field of recommendation systems has attracted significant attention. However, current text recommendation systems still face challenges in handling word distribution assumptions, preprocessing design, network inference models, and text perception technologies. Traditional RNN neural network layers often encounter issues such as gradient explosion or vanishing gradients, which hinder their ability to effectively handle long-term dependencies and reverse text inference among long texts. Therefore, this paper proposes a new type of depth-aware neural network recommendation model (Hourglass Deep-aware neural network Recommendation Model, HDARM), whose structure presents an hourglass shape. This model consists of three parts: The top of the hourglass uses Word Embedding for input through Finetune-Bert to process text embeddings as word distribution assumptions, followed by utilizing bidirectional LSTM to integrate Transformer models for learning critical information. The middle of the hourglass retains key features of network outputs through CNN layers, combined with pooling layers to extract and enhance critical information from user text. The bottom of the hourglass avoids a decline in generalization performance through deep neural network layers. Finally, the model performs pattern matching between text vectors and word embeddings, recommending texts based on their relevance. In experiments, this model improved metrics like MSE and NDCG@10 by 8.74% and 10.89% respectively compared to the optimal baseline model.

show abstract

Multi-source aggregated classification for stock price movement prediction

Cited by 61 publications

References 46 publications

A Novel Approach of Stock Price Direction and Price Prediction Based on News Sentiments

A Novel Approach of Stock Price Direction and Price Prediction Based on News Sentiments

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Hourglass pattern matching for deep aware neural network text recommendation model

Contact Info

Product

Resources

About