Lukesh Kadu, Manoj Deshpande, Vijaykumar Pawar | International Journal of Software Computing and Testing | Vol 10, Issue 02 | pp. 22-30 | ISSN: 2456-2351
Abstract
Accurately predicting stock market trends remains a significant challenge in the field of finance. Deep learning, a subset of machine learning, has emerged as a powerful tool for capturing complex relationships within data. What sets deep learning apart is its ability to handle vast amounts of data, recognize intricate features, and adapt to evolving patterns, all while uncovering hidden insights. At its core, deep learning uses artificial neural networks that mimic the learning and pattern recognition capabilities of the human brain, making them highly effective for analyzing financial data. By leveraging advanced deep neural networks, the proposed approach integrates a diverse array of market data, including historical stock prices, trading volumes, and sentiments extracted from news sources. With the introduction of social media, the financial markets have changed, with Twitter emerging as a significant platform for real-time information dissemination and sentiment expression. It predicts the sentiment in stock market tweets using advanced machine learning techniques. We present a curated dataset comprising tweets related to various stocks, encompassing a diverse range of sentiments expressed by users. Through natural language processing techniques, we preprocess the textual data to extract relevant features and mitigate noise. Subsequently, we employ state-of-the-art machine learning algorithms, including but not limited to support vector machines (SVM), random forest, and recurrent neural networks (RNNs), to model the relationship between tweet content and corresponding sentiment labels. Additionally, we investigate the impact of sentiment lexicons, word embeddings, and domain-specific features on prediction accuracy in terms of investors and financial analysts.
Keywords:Profound learning, deep learning, BERT, financial sentiment analysis, VADER lexicon
natural language processing
🔒 This is a subscription article
Full text is available to subscribers and institutional members. Please choose an option below to access it.
SubscribePurchase this articleInstitutional / Login accessReferences
- Prakash TA, Sudha. Stock price prediction using deep-learning model. 4th International Conference on Pervasive Computing and Social Networking. Salem, India. 2024, May 03-04. 533–538. IEEE. doi:10.1109/ICPCSN62568.2024.00090.
- Dhanalakshmi R, Harsh R, Prathiba SB. Predicting the price of stock using deep learning algorithms. International Conference on System, Computation, Automation and Networking. Puducherry, India. 2023, Nov 17-18. 1–6. IEEE. doi:10.1109/ICSCAN58655.2023.10395609.
- Manasa N, Praveenraj DW, SR L. Predictive analytics for stock market trends using machine learning. International Conference on Computation, Automation and Knowledge Management. Dubai, United Arab Emirates. 2023, Dec 12–13. 1–8. IEEE. doi:10.1109/ICCAKM58659.2023.10449528.
- Mannam PK. Stock exchange market performance and data analysis techniques by using machine learning approach. International Conference on Evolutionary Algorithms and Soft Computing Techniques. Bengaluru, India. 2023, Oct 20–21. 1–6. IEEE. doi:10.1109/EASCT59475.2023.10393178.
- Patnaik D, Rao NVJ, Padhiari B, Patnaik S. Stock price forecasting using machine learning techniques: A systematic review. International Conference on Data Science & Informatics. Bhubaneswar, India. 2023, Aug 12-13. 243–251. IEEE. doi:10.1109/ICDSI60108.2023.00053.
- Ekaputri AP, Akbar S. Financial news sentiment analysis using modified VADER for stock price prediction. International Conference on Advanced Informatics: Concepts, Theory and Applications. Tokoname, Japan. 2022 Sep 28–29. 1–6. IEEE. doi:10.1109/ICAICTA56449.2022.9932925.
- Weng X, Lin X, Zhao S. Stock price prediction based on LSTM and BERT. International Conference on Machine Learning and Cybernetics. Japan. 2022, Sep 9–11. 12–17. IEEE. doi:10.1109/ICMLC56445.2022.9941293
- Emioma CC, Edeki SO. Stock price prediction using machine learning on least-squares linear regression basis. J Phys Conf Ser. 2021;1734(1):012058. doi:10.1088/1742-6596/1734/1/012058.
- Mehtab S, Sen J. A time series analysis-based stock price prediction using machine learning and deep learning models. Int J Bus Forecast Mark Intell. 2020;6(4):272–335. doi:10.1504/IJBFMI.2020.115691.
- Vijh M, Chandola D, Tikkiwal VA, Kumar A. Stock closing price prediction using machine learning techniques. Procedia Comput Sci. 2020;167:599–606. doi:10.1016/j.procs.2020.03.326.
- Vazirani S, Sharma A, Sharma P. Analysis of various machine learning algorithm and hybrid model for stock market prediction using python. International Conference on Smart Technologies in Computing, Electrical and Electronics. Bengaluru, India. 2020, Oct 9–10. 203–207. IEEE. doi:10.1109/ICSTCEE49637.2020.9276859.
- Aswani R, Kar AK, Ilavarasan PV, Dwivedi YK. Search engine marketing is not all gold: Insights from Twitter and SEOClerks. Int J Inf Manag. 2018;38(1):107–116. doi:10.1016/j.ijinfomgt.2017.07.005.
- Shah HN. Prediction of stock market using artificial intelligence. International Conference for Convergence in Technology. Bombay, India. 2019, Mar 29–31. 1–6. IEEE. doi:10.1109/I2CT45611.2019.9033776.
- Sirimevan N, Mamalgaha IG, Jayasekara C, Mayuran YS, Jayawardena C. Stock market prediction using machine learning techniques. International Conference on Advancements in Computing. Malabe, Sri Lanka. 2019, Dec 5–7. 192–197. IEEE. doi:10.1109/ICAC49085.2019.9103381.
How to cite this article
@article{KaduL2024,
author = {Lukesh Kadu and Manoj Deshpande and Vijaykumar Pawar},
title = {Forecasting Trends in the Stock Market by Using Deep Learning Approaches},
journal = {International Journal of Software Computing and Testing},
year = {2024},
volume = {10},
number = {02},
pages = {22--30},
issn = {2456-2351},
url = {https://journalspub.com/publication/ijsct/article=11078}
}