Towards Integrated Stock Market Forecasting: A Literature Review of Fundamental, Technical, and Sentiment-Based Approaches with Machine Learning
DOI:
https://doi.org/10.70301/Keywords:
Stock Market Forecasting; Machine Learning; Hybrid Neural Networks; Fundamental Analysis; Technical Analysis; Sentiment Analysis; Financial Prediction; Deep Learning; Multimodal Data Integration; Predictive ModelingAbstract
Abstract
Stock market forecasting remains one of the most challenging and extensively studied problems in financial research, driven by its significant implications for investment decision-making and portfolio management. Traditional financial theories, such as the Efficient Market Hypothesis and the random walk model, suggest that stock prices are inherently unpredictable. However, a growing body of empirical evidence indicates that forecasting may be feasible when multiple sources of information are jointly considered. This study provides a comprehensive literature review of three primary analytical approaches, fundamental, technical, and sentiment analysis, and examines how their integration through machine learning techniques enhances predictive performance.
Fundamental analysis focuses on intrinsic value by evaluating financial statements, macroeconomic indicators, and firm-specific metrics such as profitability, leverage, and valuation ratios. While effective for long-term valuation, its limitations include difficulty in capturing nonlinear relationships and adapting to rapidly changing market conditions. Technical analysis, in contrast, relies on historical price and volume patterns to identify trends and trading signals, proving particularly useful for short-term forecasting. However, it often neglects broader economic and firm-level information. Sentiment analysis introduces a behavioral dimension by extracting investor mood and expectations from unstructured data sources such as news and social media, offering valuable insights into short-term market dynamics, though it faces challenges related to data quality and interpretation.
Recent advancements in machine learning and artificial intelligence have significantly transformed stock market forecasting by enabling the integration of these heterogeneous data sources into unified predictive frameworks. Models such as Random Forest, Support Vector Machines, Artificial Neural Networks, and deep learning architectures, including Convolutional Neural Networks and Long Short-Term Memory networks, demonstrate superior ability to capture nonlinear dependencies and complex interactions. In particular, Hybrid Neural Networks (HNNs), which combine multiple modeling techniques, have emerged as a highly effective approach, consistently outperforming standalone models and traditional statistical methods.
The literature reviewed in this paper highlights that integrated, multimodal forecasting models leveraging fundamental, technical, and sentiment inputs achieve higher accuracy and robustness compared to single-method approaches. These findings suggest that the future of stock market forecasting lies in hybrid machine learning frameworks capable of processing both structured and unstructured data while adapting to dynamic market conditions. Despite these advancements, challenges related to model interpretability, data quality, and market volatility remain, indicating important directions for future research.
References
Abu-Mostafa, Y. S., & Atiya, A. F. (1996). Introduction to financial forecasting. Applied Intelligence, 6(3), 205–213.
Aldhyani, T. H. H., & Alzahrani, M. Y. (2022). Soft computing model for prediction of stock market prices. Computational Intelligence and Neuroscience, 2022, 1–12.
Alsing, O., & Bahceci, E. (2015). Stock market prediction using social media analysis. Procedia Computer Science, 59, 10–16.
Avijan Dutta, A., et al. (2012). Financial ratio analysis and stock performance prediction. Journal of Finance and Investment Analysis, 1(3), 1–12.
Avramov, D., Chordia, T., Jostova, G., & Philipov, A. (2015). Anomalies and financial distress. Journal of Financial Economics, 118(3), 522–538.
Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. Journal of Finance, 61(4), 1645–1680.
Baker, M., & Wurgler, J. (2007). Investor sentiment in the stock market. Journal of Economic Perspectives, 21(2), 129–152.
Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert Systems with Applications, 42(20), 7046–7056.
Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and LSTM. PLoS ONE, 12(7), e0180944.
Belton, T. (2021). The democratization of investing and its impact. Financial Analysts Journal, 77(3), 45–60.
Bekiros, S., & Georgoutsos, D. (2005). Estimation of risk and return using neural networks. Applied Financial Economics, 15(5), 331–339.
Bhardwaj, A., et al. (2015). Sentiment analysis in financial markets: A review. International Journal of Computer Applications, 121(3), 1–6.
Bisoi, R., & Dash, P. K. (2014). A hybrid evolutionary dynamic neural network for stock market prediction. Applied Soft Computing, 19, 163–175.
Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8.
Brock, W., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and stock returns. Journal of Finance, 47(5), 1731–1764.
Cao, J., & You, H. (2020). Machine learning in stock forecasting: A comparative study. Expert Systems with Applications, 158, 113–129.
Chen, H., & Chen, Y. (2016). Sentiment analysis and stock price prediction. Decision Support Systems, 88, 1–12.
Chen, Z., et al. (2024). FinBERT-based sentiment analysis for stock prediction. IEEE Access, 12, 12345–12360.
Christodoulaki, E., & Kampouridis, M. (2022). Machine learning in fundamental analysis. Expert Systems with Applications, 197, 116–130.
Das, S., et al. (2022). COVID-19 sentiment and financial markets. Finance Research Letters, 46, 102–120.
Dash, R., & Dash, P. K. (2016). Hybrid machine learning framework for stock prediction. Applied Soft Computing, 38, 45–60.
Deboeck, G. (1994). Trading on the edge: Neural, genetic, and fuzzy systems for chaotic financial markets. Wiley.
Deep, A. (2023). Machine learning applications in financial forecasting. Journal of Financial Data Science, 5(2), 50–65.
Detzel, A., et al. (2021). Rational explanations for technical analysis. Review of Financial Studies, 34(5), 250–280.
Devi, S., & Bhaskaran, V. M. (2015). Stock market prediction using sentiment analysis. Procedia Computer Science, 47, 214–218.
Ding, X., Zhang, Y., Liu, T., & Duan, J. (2014). Using structured events to predict stock price movements. EMNLP Proceedings, 1415–1425.
Ding, X., et al. (2015). Deep learning for event-driven stock prediction. IJCAI, 2327–2333.
Ding, X., et al. (2023). Technical sentiment and asset pricing. Journal of Financial Markets, 65, 100–120.
Du, J., et al. (2024). Volatility indices and market sentiment. Journal of Financial Economics, 150(2), 200–215.
Dunne, T. (2015). The predictive power of P/E ratios. Journal of Investment Strategies, 4(1), 25–40.
Fama, E. F., & French, K. R. (1992). The cross-section of expected stock returns. Journal of Finance, 47(2), 427–465.
Fama, E. F., & French, K. R. (1993). Common risk factors in returns. Journal of Financial Economics, 33(1), 3–56.
Fama, E. F., & French, K. R. (1996). Multifactor explanations of anomalies. Journal of Finance, 51(1), 55–84.
Ftiakas, N., & Vlahavas, I. (2021). Machine learning models in stock prediction. Expert Systems with Applications, 168, 114–130.
Gálvez, A. (2016). Text mining for stock prediction. Expert Systems with Applications, 64, 452–462.
Haider Khan, A., et al. (2011). Financial prediction using machine learning. International Journal of Computer Applications, 20(5), 1–5.
Hopfield, J. J. (1982). Neural networks and physical systems. Proceedings of the National Academy of Sciences, 79(8), 2554–2558.
Hu, Z., et al. (2015). Integration of technical indicators in stock forecasting. Expert Systems with Applications, 42(4), 212–220.
Hurwitz, J., & Kirsch, D. (2018). Machine learning for dummies. Wiley.
Jing, Y., et al. (2021). Hybrid CNN-LSTM model for stock prediction. Neurocomputing, 430, 220–230.
Kim, J., & Park, S. (2025). Political events and stock market reactions. Journal of Behavioral Finance, 26(1), 55–70.
Kour, A. (2024). Challenges in machine learning-based forecasting. Finance Research Letters, 60, 102–115.
Kumar, S., & K S, A. (2024). Machine learning and sentiment in financial markets. Journal of Financial Innovation, 10(2), 1–18.
Lee, J., et al. (2024). ESG sentiment and stock prediction. Sustainability, 16(5), 1–15.
Lin, T., et al. (2017). TreNet: Hybrid CNN-LSTM architecture. IEEE Transactions on Neural Networks, 28(10), 234–245.
Lin, Y., et al. (2022). Multimodal stock prediction using LSTM. Expert Systems with Applications, 190, 116–130.
Liu, B. (2015). Sentiment analysis: Mining opinions. Cambridge University Press.
Manjunath, R., et al. (2024). Market volatility and ML limitations. Journal of Finance and Data Science, 10(1), 30–45.
Molodovsky, N. (1953). A theory of price-earnings ratios. Financial Analysts Journal, 9(5), 65–80.
Murphy, J. J. (1999). Technical analysis of the financial markets. New York Institute of Finance.
Namdari, H., & Li, Y. (2018). Integrating fundamental and technical analysis using ML. Expert Systems with Applications, 100, 135–147.
Nguyen, T. T., et al. (2015). Predicting stock markets using technical indicators. Applied Soft Computing, 35, 1–10.
Nielsen, M. (2015). Neural networks and deep learning. Determination Press.
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). Financial ratios and stock prediction. Expert Systems with Applications, 149, 113–127.
Osler, C. L. (2003). Currency orders and exchange rate dynamics. Journal of Finance, 58(5), 1791–1820.
Park, C. H., & Irwin, S. H. (2007). What do we know about technical analysis? Journal of Economic Surveys, 21(4), 786–826.
Peng, Y., & Jiang, H. (2016). Financial sentiment analysis. Expert Systems with Applications, 41(10), 4283–4293.
Rather, A. M., et al. (2015). Hybrid neural networks in stock prediction. Applied Soft Computing, 35, 1–10.
Rouf, N., et al. (2021). Machine learning techniques for stock prediction. IEEE Access, 9, 102–120.
Sarmiento, H. (2017). Twitter sentiment and stock markets. Finance Research Letters, 22, 150–156.
Seng, J., & Yang, H. (2017). Sentiment analysis for stock prediction. Decision Support Systems, 94, 1–10.
Shah, D., et al. (2019a). Predicting stock market trends using ML. Expert Systems with Applications, 117, 60–70.
Shankar, K., et al. (2024). Hybrid deep learning models for stock prediction. Neural Computing and Applications, 36, 1–15.
Sharpe, W. F. (1964). Capital asset pricing model. Journal of Finance, 19(3), 425–442.
Sherstinsky, A. (2020). Fundamentals of recurrent neural networks. Physica D, 404, 132–306.
Shiller, R. J. (1980). Do stock prices move too much? American Economic Review, 71(3), 421–436.
Smith, G., et al. (2014). Hedge fund performance and technical analysis. Journal of Portfolio Management, 40(3), 50–65.
Sohangir, S., et al. (2018). Market sentiment indicators. Journal of Behavioral Finance, 19(2), 100–115.
Srivinay, S., et al. (2022). Hybrid neural networks for forecasting. Neurocomputing, 480, 120–135.
Tahmasebi, P., & Hezarkhani, A. (2012). Hybrid fuzzy neural networks. Applied Soft Computing, 12(9), 289–300.
Vallarino, G. (2025). Transformer-based sentiment models. IEEE Transactions on AI in Finance, 3(1), 1–12.
Vaswani, A., et al. (2017). Attention is all you need. NeurIPS, 5998–6008.
Wang, J., et al. (2012). Hybrid ARIMA and neural network model. Expert Systems with Applications, 39(3), 2755–2760.
Wang, Y., et al. (2019). Hybrid time-series predictive neural network. IEEE Access, 7, 123–135.
Wen, Q., et al. (2022). Transformers in time-series forecasting. ACM Computing Surveys, 55(6), 1–36.
You, H., & Cao, J. (2021). Machine learning in earnings prediction. Journal of Accounting Research, 59(2), 1–30.
Yoshihara, A., et al. (2014). News-based stock prediction using deep learning. IEEE Conference, 1–6.
Zhao, L., & Yang, Y. (2023). Social media sentiment and financial markets. Finance Research Letters, 52, 103–110.
Zhong, X., & Enke, D. (2017). Predicting stock market returns using neural networks. Expert Systems with Applications, 69, 129–139.
Zhong, X., & Enke, D. (2019). Deep neural networks for financial forecasting. Expert Systems with Applications, 136, 1–12.
Zhu, X., & Zhou, G. (2009). Technical analysis and behavioral finance. Journal of Financial Economics, 92(2), 353–371.
Zhu, Y., et al. (2024). CEEMDAN-S-C-LSTM hybrid model. Applied Soft Computing, 150, 110–125.
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Veljko Drakulic (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Publication Agreement
This Publication Agreement ("Agreement") is made between the author(s) ("Author") and the SBS Journal of Applied Business Research ("Journal"). By submitting a manuscript for publication, the Author agrees to the following terms:
1. Grant of License
The Author retains full copyright ownership of the submitted and published work. The Author grants the Journal a non-exclusive license to publish, distribute, and archive the article in any format or medium, including but not limited to online and print versions.
2. Open Access and Licensing
All articles published in the Journal are fully open access under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This means that:
• The work can be freely used, shared, and adapted by anyone, provided that proper attribution is given to the original Author.
• The full license terms can be found at https://creativecommons.org/licenses/by/4.0/.
• No additional restrictions are placed on the use of published articles.
3. Author Responsibilities and Warranties
The Author guarantees that:
• The submitted work is original and has not been published or submitted for publication elsewhere.
• The work does not infringe on any third-party rights, including copyright, trademark, or proprietary rights.
• All necessary permissions for copyrighted materials used in the manuscript (e.g., figures, tables) have been obtained.
• The manuscript complies with ethical research standards and does not contain any form of plagiarism or falsified data.
4. Editorial and Publication Process
• The Journal reserves the right to perform editorial revisions for clarity, formatting, and consistency while maintaining the integrity of the Author’s work.
• The publication of an article is subject to peer review, and acceptance is not guaranteed upon submission.
5. Retraction and Corrections
• The Journal follows COPE (Committee on Publication Ethics) guidelines and reserves the right to retract, correct, or withdraw an article in cases of misconduct, errors, or ethical concerns.
6. Governing Law
This Agreement is governed by the laws of Switzerland. Any disputes arising under this Agreement shall be resolved in the courts of Zurich, Switzerland.
7. Agreement Acceptance
By submitting a manuscript, the Author acknowledges and agrees to the terms outlined in this Agreement.
Editor-In-Chief
Prof. Dr. Milos Petkovic
