Designing a Stock Return Prediction Model Based on the Integration of Deep Learning, Investor Sentiment Analysis, and Historical Financial Data
Keywords:
Stock return, deep learning, investor sentiment analysis, historical financial data, capital market, financial predictionAbstract
This study aimed to design a conceptual model for stock return prediction based on the integration of deep learning, investor sentiment analysis, and historical financial data. This qualitative study was conducted using thematic analysis. Participants consisted of 19 experts from the capital market, including financial analysts, portfolio managers, financial data scientists, and university faculty members in finance from Tehran. Participants were selected through purposive sampling. Data were collected using semi-structured interviews and the interview process continued until theoretical saturation was achieved. The average duration of each interview was 55 minutes. After transcription, the interview data were coded and analyzed using NVivo software. To enhance the trustworthiness of the findings, member checking, peer review, audit trail documentation, and constant comparison of codes were applied. Data analysis led to the identification of five main categories: “data-driven architecture of return prediction,” “integration of investor sentiment with historical financial data,” “deep learning capability in detecting nonlinear patterns,” “model risk control, overfitting, and prediction stability,” and “institutional implementation requirements and investment decision-making.” The findings indicated that stock return prediction cannot rely solely on historical prices and technical indicators. Instead, combining structured financial data with unstructured sentiment-based data can improve the informational richness and predictive quality of return signals. Participants also emphasized the importance of model interpretability, periodic retraining, data bias control, and human oversight in algorithmic investment decisions. The results suggest that an effective stock return prediction model should be hybrid, dynamic, multi-source, and interpretable. Such a model can support investment decision-making only when deep learning, sentiment analysis, and historical financial data are integrated within a coherent framework of data governance, continuous validation, and algorithmic risk management.
Downloads
References
Araci, D. (2019). FinBERT: Financial sentiment analysis with pre-trained language models. arXiv. https://arxiv.org/abs/1908.10063
Bollen, J., Mao, H., & Zeng, X. J. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8. https://doi.org/10.1016/j.jocs.2010.12.007
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383–417. https://doi.org/10.2307/2325486
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009
Guest, G., Bunce, A., & Johnson, L. (2006). How many interviews are enough? An experiment with data saturation and variability. Field Methods, 18(1), 59–82. https://doi.org/10.1177/1525822X05279903
Henrique, B. M., Sobreiro, V. A., & Kimura, H. (2019). Literature review: Machine learning techniques applied to financial market prediction. Expert Systems with Applications, 124, 226–251. https://doi.org/10.1016/j.eswa.2019.01.012
Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 116659. https://doi.org/10.1016/j.eswa.2022.116659
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. SAGE Publications.
Lo, A. W. (2004). The adaptive markets hypothesis: Market efficiency from an evolutionary perspective. Journal of Portfolio Management, 30(5), 15–29. https://doi.org/10.3905/jpm.2004.442611
Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. The Journal of Finance, 66(1), 35–65. https://doi.org/10.1111/j.1540-6261.2010.01625.x
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing, 90, 106181. https://doi.org/10.1016/j.asoc.2020.106181
Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139–1168. https://doi.org/10.1111/j.1540-6261.2007.01232.x
