Hybrid AI Models Combining Financial NLP and Time-Series Forecasting for Stock Advisory
DOI:
https://doi.org/10.63397/ISCSITR-IJSRAIML_2023_04_01_005Keywords:
Financial NLP, Time-Series Forecasting, Stock Prediction, Hybrid AI Models, Sentiment Analysis, LSTM, Transformer, BERT, Robo-advisors, Deep Learning in FinanceAbstract
The convergence of Natural Language Processing (NLP) and time-series forecasting within financial domains has enabled the emergence of advanced, intelligent stock advisory systems. This paper explores hybrid AI architectures that synthesize structured time-series data with unstructured financial text (e.g., news, earnings reports, social media). By combining models such as LSTM, BERT, and transformers, along with optimization algorithms like genetic algorithms or reinforcement learning, hybrid approaches offer enhanced accuracy, interpretability, and robustness. This paper reviews literature prior to 2023, analyzes state-of-the-art architectures, compares predictive performance across domains, and proposes a novel framework combining sentiment signals and historical patterns for stock advisories.
References
Araci, D. (2019). FinBERT: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063.
Apu, K. U., Rahman, M. M., & Hoque, A. B. (2022). Forecasting future investment value with machine learning, neural networks, and ensemble learning: A meta-analytic study. Review
of Applied Science and Technology, 4(2), 13–28. https://rast-journal.org
Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8.
Box, G. E. P., & Jenkins, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley.
Cao, L. (2022). AI in finance: Challenges, techniques, and opportunities. ACM Computing Surveys, 55(4), Article 88. https://doi.org/10.1145/3502289
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383–417.
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.
Ko, C. R., & Chang, H. T. (2021). LSTM-based sentiment analysis for stock price forecast. PeerJ Computer Science, 7, e408. https://doi.org/10.7717/peerj-cs.408
Leow, E. K. W., Nguyen, B. P., & Chua, M. C. H. (2021). Robo-advisor using genetic algorithm and BERT sentiments from tweets for hybrid portfolio optimisation. Expert Systems with Applications, 185, 115652. https://doi.org/10.1016/j.eswa.2021.115652
Lim, B., Arik, S. Ö., Loeff, N., & Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748–1764.
Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., & Ngo, D. C. L. (2014). Text mining for market prediction: A systematic review. Expert Systems with Applications, 41(16), 7653–7670.
Ni, H., Wang, S., & Cheng, P. (2021). A hybrid approach for stock trend prediction based on tweets embedding and historical prices. World Wide Web, 24(5), 1523–1541. https://doi.org/10.1007/s11280-021-00880-9
Qiu, J., Wang, B., & Zhou, C. (2020). Forecasting stock prices with long-short term memory neural network based on attention mechanism. PLOS ONE, 15(1), e0227222. https://doi.org/10.1371/journal.pone.0227222
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.
Sesen, M. B., Romahi, Y., & Li, V. (2019). Natural language processing of financial news. In T. Guida (Ed.), Big Data and Machine Learning in Quantitative Investment (pp. 185–202). Wiley.
