A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction
Stock market analysis plays an indispensable role in gaining knowledge about the stock market, developing trading strategies, and determining the intrinsic value of stocks. Nevertheless, predicting stock trends remains extremely difficult due to a variety of influencing factors, volatile market news...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/2/250 |
| _version_ | 1797494515732316160 |
|---|---|
| author | Mohammad Kamel Daradkeh |
| author_facet | Mohammad Kamel Daradkeh |
| author_sort | Mohammad Kamel Daradkeh |
| collection | DOAJ |
| description | Stock market analysis plays an indispensable role in gaining knowledge about the stock market, developing trading strategies, and determining the intrinsic value of stocks. Nevertheless, predicting stock trends remains extremely difficult due to a variety of influencing factors, volatile market news, and sentiments. In this study, we present a hybrid data analytics framework that integrates convolutional neural networks and bidirectional long short-term memory (CNN-BiLSTM) to evaluate the impact of convergence of news events and sentiment trends with quantitative financial data on predicting stock trends. We evaluated the proposed framework using two case studies from the real estate and communications sectors based on data collected from the Dubai Financial Market (DFM) between 1 January 2020 and 1 December 2021. The results show that combining news events and sentiment trends with quantitative financial data improves the accuracy of predicting stock trends. Compared to benchmarked machine learning models, CNN-BiLSTM offers an improvement of 11.6% in real estate and 25.6% in communications when news events and sentiment trends are combined. This study provides several theoretical and practical implications for further research on contextual factors that influence the prediction and analysis of stock trends. |
| first_indexed | 2024-03-10T01:35:25Z |
| format | Article |
| id | doaj.art-4cda20c58bca448ba369952eddd5fb7d |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T01:35:25Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-4cda20c58bca448ba369952eddd5fb7d2023-11-23T13:34:39ZengMDPI AGElectronics2079-92922022-01-0111225010.3390/electronics11020250A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend PredictionMohammad Kamel Daradkeh0Department of Information Technology, University of Dubai, Dubai 14143, United Arab EmiratesStock market analysis plays an indispensable role in gaining knowledge about the stock market, developing trading strategies, and determining the intrinsic value of stocks. Nevertheless, predicting stock trends remains extremely difficult due to a variety of influencing factors, volatile market news, and sentiments. In this study, we present a hybrid data analytics framework that integrates convolutional neural networks and bidirectional long short-term memory (CNN-BiLSTM) to evaluate the impact of convergence of news events and sentiment trends with quantitative financial data on predicting stock trends. We evaluated the proposed framework using two case studies from the real estate and communications sectors based on data collected from the Dubai Financial Market (DFM) between 1 January 2020 and 1 December 2021. The results show that combining news events and sentiment trends with quantitative financial data improves the accuracy of predicting stock trends. Compared to benchmarked machine learning models, CNN-BiLSTM offers an improvement of 11.6% in real estate and 25.6% in communications when news events and sentiment trends are combined. This study provides several theoretical and practical implications for further research on contextual factors that influence the prediction and analysis of stock trends.https://www.mdpi.com/2079-9292/11/2/250stock market predictiondata analyticssentiment analysismulti-feature fusionbidirectional long short-term memoryconvolution neural network |
| spellingShingle | Mohammad Kamel Daradkeh A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction Electronics stock market prediction data analytics sentiment analysis multi-feature fusion bidirectional long short-term memory convolution neural network |
| title | A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction |
| title_full | A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction |
| title_fullStr | A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction |
| title_full_unstemmed | A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction |
| title_short | A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction |
| title_sort | hybrid data analytics framework with sentiment convergence and multi feature fusion for stock trend prediction |
| topic | stock market prediction data analytics sentiment analysis multi-feature fusion bidirectional long short-term memory convolution neural network |
| url | https://www.mdpi.com/2079-9292/11/2/250 |
| work_keys_str_mv | AT mohammadkameldaradkeh ahybriddataanalyticsframeworkwithsentimentconvergenceandmultifeaturefusionforstocktrendprediction AT mohammadkameldaradkeh hybriddataanalyticsframeworkwithsentimentconvergenceandmultifeaturefusionforstocktrendprediction |