A Framework for Market State Prediction with Ontological Asset Selection: A Multimodal Approach
Source abstract
Abstract
In this study, we introduce a detailed framework for predicting market conditions and selecting stocks by integrating machine learning techniques with ontological financial analysis. The process starts with ontology-based stock selection, categorizing companies using fundamental financial indicators such as liquidity, profitability, debt ratios, and growth metrics. For instance, firms showcasing favorable debt-to-equity ratios along with robust revenue growth are identified as high-performing entities. This classification facilitates targeted analyses of market dynamics. To predict market states—categorizing them into bull, bear, or neutral phases—the framework utilizes a Non-Stationary Markov Chain (NMC), BERT, to assess sentiment in financial news articles and Long Short-Term Memory (LSTM) networks to identify temporal patterns. Key inputs like the Sentiment Index (SI) and Illiquidity Index (ILLIQ) play essential roles in dynamically influencing regime predictions within the NMC model; these inputs are supplemented by variables including GARCH volatility and VIX to enhance predictive precision further still. Empirical findings demonstrate that our approach achieves an impressive 97.20% accuracy rate for classifying market states, significantly surpassing traditional methods like Naive Bayes, Logistic Regression, KNN, Decision Tree, ANN, Random Forest, and XGBoost. The state-predicted strategy leverages this framework to dynamically adjust portfolio positions based on projected market conditions. It prioritizes growth-oriented assets during bull markets, defensive assets in bear markets, and maintains balanced portfolios in neutral states. Comparative testing showed that this approach achieved an average cumulative return of 13.67%, outperforming the Buy and Hold method’s return of 8.62%. Specifically, for the S&P 500 index, returns were recorded at 6.36% compared with just a 1.08% gain from Buy and Hold strategies alone. These results underscore the robustness of our framework and its potential advantages for improving decision-making within quantitative trading environments as well as asset selection processes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Stock Market Forecasting Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Polytechnic School of Pernambuco, POLI/UPE, Rua Benfica, 455, Recife 50720-001, Pernambuco, Brazil
FITec—Technological Innovations, Cais do Apolo, 222-12º andar, Recife 50030-230, Pernambuco, Brazil
Funding
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brazil (CAPES) · Fundação de Amparo a Ciência e Tecnologia do Estado de Pernambuco (FACEPE) · Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)—Brazilian research agencies
References (49)
Show source-provided references
1. Yu, S., and Li, Z. (2018). Forecasting Stock Price Index Volatility with LSTM Deep Neural Network. Recent Developments in Data Science and Business Analytics: Proceedings of the International Conference on Data Science and Business Analytics (ICDSBA-2017), Springer. Springer Proceedings in Business and Economics.10.1007/978-3-319-72745-5_29 ↗
2. Forecasting the Volatility of Stock Price Index: A Hybrid Model Integrating LSTM with Multiple GARCH-Type Models10.1016/j.eswa.2018.03.002 ↗
3. Joshi, A., and Pradhan, P.C. (2023). Stock Selection Using Ontological Financial Analysis. Advances in Data Science and Computing Technologies, Springer.
4. Forecasting the Market with Machine Learning Algorithms: An Application of NMC-BERT-LSTM-DQN-X Algorithm in Quantitative Trading10.1145/3488378 ↗
5. Guo, T., and Lin, T. (2018). Multi-variable LSTM Neural Network for Autoregressive Exogenous Model. arXiv.
6. A Self-Attention-LSTM Method for Dam Deformation Prediction Based on CEEMDAN Optimization10.1016/j.asoc.2024.111615 ↗
7. Sousa, M.G., Sakiyama, K., Rodrigues, L.S., Moraes, P.H., Fernandes, E.R., and Matsubara, E.T. (2019, January 4–6). BERT for Stock Market Sentiment Analysis. Proceedings of the 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, USA.10.1109/ICTAI.2019.00231 ↗
8. Zhou, J. (2023). Sentiment Index Construction and the Influence of Sentiments on Returns. Proceedings of the 2nd International Conference on Business and Policy Studies, Springer Nature Singapore Pte Ltd.10.1007/978-981-99-6441-3_146 ↗
9. Gerber, M.C., Gerber, A.J., and van der Merwe, A. (2015, January 13–15). The Conceptual Framework for Financial Reporting as a Domain Ontology. Proceedings of the Twenty-First Americas Conference on Information Systems, Fajardo, Puerto Rico.
10. Supervised Machine Learning Method for Ontology-Based Financial Decisions in the Stock Market10.1145/3554733 ↗
11. Wani, H., and Sujithkumar, S.H. (2022, January 26–27). An Integrated Machine Learning Approach Predicting Stock Values Using Order Book Details. Proceedings of the International Conference on Data Science and Applications, Kolkata, India.10.1007/978-981-19-6634-7_10 ↗
12. Roszyk, N., and Slepaczuk, R. (2024). The Hybrid Forecast of S&P 500 Volatility Ensembled from VIX, GARCH and LSTM Models. arXiv.10.2139/ssrn.4903194 ↗
13. Mero, K., Salgado, N., Meza, J., Pacheco-Delgado, J., and Ventura, S. (2024). Unemployment Rate Prediction Using a Hybrid Model of Recurrent Neural Networks and Genetic Algorithms. Appl. Sci., 14.10.3390/app14083174 ↗
14. Financial Time Series Forecasting via CEEMDAN-LSTM with Exogenous Features
15. Mirmozaffari, M., Yazdani, M., Boskabadi, A., Dolatsara, H.A., Kabirifar, K., and Golilarz, N.A. (2020). A Novel Machine Learning Approach Combined with Optimization Models for Eco-efficiency Evaluation. Appl. Sci., 10.10.3390/app10155210 ↗
16. A Novel Artificial Intelligent Approach: Comparison of Machine Learning Tools and Algorithms Based on Optimization DEA Malmquist Productivity Index for Eco-Efficiency Evaluation10.1108/IJESM-02-2020-0003 ↗
17. Gorgolis, N., Hatzilygeroudis, I., Istenes, Z., and Gyenne, L.-G. (2019, January 15–17). Hyperparameter Optimization of LSTM Network Models through Genetic Algorithm. Proceedings of the 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece.10.1109/IISA.2019.8900675 ↗
18. Dudycz, H., and Korczak, J. (2015, January 13–16). Conceptual Design of Financial Ontology. Proceedings of the 2015 Federated Conference on Computer Science and Information Systems (FedCSIS), Lodz, Poland.
19. Norberg, R. (1999). A Markov Chain Financial Market, Laboratory of Actuarial Mathematics, University of Copenhagen. Working Paper.
20. Modelling Dependence with Copulas and Applications to Risk Management
21. Copula Concepts in Financial Markets
22. Kim, S., and Kang, M. (2019). Financial Series Prediction Using Attention LSTM. arXiv.
23. Stock Market Prediction by Incorporating News Sentiments Using BERT
24. Multimodal Deep Learning for Finance: Integrating and Forecasting International Stock Markets10.1007/s11227-019-03101-3 ↗
25. Qin, J. (2024). MSMF: Multi-Scale Multi-Modal Fusion for Enhanced Stock Market Prediction. arXiv.
26. Machine Learning in Business and Finance: A Literature Review and Research Opportunities10.1186/s40854-024-00629-z ↗
27. Usmonov, B. (2023). The Impact of the Financial Ratios on the Financial Performance. A Case of Chevron Corporation (CVX). International Conference on Internet of Things, Smart Spaces, and Next Generation Networks and Systems, Proceedings of the 23rd International Conference, NEW2AN 2023, and 16th Conference, ruSMART 2023, Dubai, United Arab Emirates, 21–22 December 2023, Springer Nature.
28. Costa, K. (2023). Anomaly Detection in Global Financial Markets with Graph Neural Networks and Nonextensive Entropy. arXiv.
29. Turiel, J.D., and Aste, T. (2021). Self-Organised Criticality in High Frequency Finance: The Case of Flash Crashes. arXiv.10.3390/e24020257 ↗
30. On the Effectiveness of Dimensionality Reduction Techniques on High Dimensionality Datasets
31. Overview and Comparative Study of Dimensionality Reduction Techniques for High Dimensional Data10.1016/j.inffus.2020.01.005 ↗
32. Data Compression and Visualization Using PCA and t-SNE
33. Classifying and Grouping Narratives with Convolutional Neural Networks, PCA and t-SNE
34. Illiquidity and the Measurement of Stock Price Synchronicity10.1111/1911-3846.12519 ↗
35. Illiquidity and Stock Returns II: Cross-Section and Time-Series Effects
36. Alaparthi, S., and Mishra, M. (2020). Bidirectional Encoder Representations from Transformers (BERT): A Sentiment Analysis Odyssey. arXiv.
37. Enhancing Stock Trend Prediction Using BERT-Based Sentiment Analysis and Machine Learning Techniques10.46336/ijqrm.v5i1.567 ↗
38. A Copula-Based Markov Chain Model for Serially Dependent Event Times with a Dependent Terminal Event10.1007/s42081-020-00087-8 ↗
39. Ghazali, R., Nawi, N.M., Deris, M.M., Abawajy, J.H., and Arbaiy, N. (2024). Text Sentiment Analysis on VIX’s Impact on Market Sentiment Dynamics. Recent Advances on Soft Computing and Data Mining, Springer Nature.10.1007/978-3-031-66965-1 ↗
40. Huang, C., Chan, Y.W., and Yen, N. (2021). Volatility Modeling of S&P500 Returns: A Comparative Study of GARCH Family Models and VIX. 2020 International Conference on Data Processing Techniques and Applications for Cyber-Physical Systems, Springer.10.1007/978-981-16-1726-3 ↗
41. Corazza, M., Perna, C., Pizzi, C., and Sibillo, M. (2022). Forecasting VIX with Hurst Exponent. Mathematical and Statistical Methods for Actuarial Sciences and Finance, Springer International Publishing.10.1007/978-3-030-99638-3 ↗
42. More, G.S., and Bartakke, P. (2023). Real-Time Implementation of Automatic License Plate Recognition System. International Conference on Advances and Applications of Artificial Intelligence and Machine Learning, Springer Nature.10.1007/978-981-99-5974-7_47 ↗
43. Li, B. (2024). Optimizing Embedded Neural Network Models. Embedded Artificial Intelligence: Principles, Platforms and Practices, Springer.10.1007/978-981-97-5038-2 ↗
44. Guinea-Cabrera, M.A., and Holgado-Terriza, J.A. (2024). Digital Twins in Software Engineering—A Systematic Literature Review and Vision. Appl. Sci., 14.10.3390/app14030977 ↗
45. Illiquidity and Stock Returns: Cross-Section and Time-Series Effects10.1016/S1386-4181(01)00024-6 ↗
46. Kumar, I., Dogra, K., Utreja, C., and Yadav, P. (2018, January 20–21). A Comparative Study of Supervised Machine Learning Algorithms for Stock Market Trend Prediction. Proceedings of the 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), Coimbatore, India.10.1109/ICICCT.2018.8473214 ↗
47. Predicting Stock Market Trends Using Machine Learning and Deep Learning Algorithms via Continuous and Binary Data: A Comparative Analysis10.1109/ACCESS.2020.3015966 ↗
48. The Impact of High-Frequency Trading on Modern Securities Markets10.1007/s12599-022-00768-6 ↗
49. High-Frequency Trading in Bond Returns: A Comparison Across Alternative Methods and Fixed-Income Markets10.1007/s10614-023-10502-3 ↗