A Comparative Study of Traditional Statistical Methods and Machine Learning Techniques for Improved Predictive Models

Article Sidebar

PDF
DOI: https://doi.org/10.28924/2291-8639-23-2025-18
Published: Jan 27, 2025
Cite as:
Bader S Alanazi, A Comparative Study of Traditional Statistical Methods and Machine Learning Techniques for Improved Predictive Models, Int. J. Anal. Appl., 23 (2025), 18.

Main Article Content

Bader S Alanazi

Abstract

The financial sector has undergone a major transformation through the incorporation of machine learning (ML) techniques, improving decision-making and predictive accuracy. This research explores the application of several ML algorithms to a dataset of historical stock prices to forecast future price movements. We conduct a comparative analysis of traditional models, including linear regression, and advanced ML techniques, including random forests, decision trees, and approaches like Long Short-Term Memory (LSTM) networks. Our analysis reveals that while traditional models establish a baseline, advanced techniques substantially outperform them regarding accuracy and reliability. This research also emphasizes the ethical challenges of using machine learning in finance, particularly in terms of model interpretability and data privacy.

Article Details

References

  1. B.O. Adelakun, Ethical Considerations in the Use of AI for Auditing: Balancing Innovation and Integrity, Eur. J. Account. Audit. Finance Res. 10 (2022), 91-108.
  2. J.M. Budd, C.M. Chu, K. Dali, H. O’Brien, Making an Impact through Experiential Learning, Proc. Assoc. Inf. Sci. Technol. 52 (2015), 1–4. https://doi.org/10.1002/pra2.2015.14505201007.
  3. K. He, Q. Yang, L. Ji, J. Pan, Y. Zou, Financial Time Series Forecasting with the Deep Learning Ensemble Model, Mathematics 11 (2023), 1054. https://doi.org/10.3390/math11041054.
  4. C. Koskinen, M. Koskinen, M. Koivula, et al. Health and Social Care Educators’ Ethical Competence, Nurs. Ethics. 27 (2020), 1115–1126. https://doi.org/10.1177/0969733019871678.
  5. K. Kulju, M. Stolt, R. Suhonen, H. Leino-Kilpi, Ethical Competence: A Concept Analysis, Nurs. Ethics 23 (2016), 401–412. https://doi.org/10.1177/0969733014567025.
  6. Falsk Raza, Machine Learning for Financial Forecasting, ResearchGate, (2023). https://doi.org/10.13140/RG.2.2.35701.96483.
  7. R. Kumar, Machine Learning Algorithms for Algorithmic Trading: An Empirical Study, Int. J. Interdiscip. Finance Insights 3 (2024), 3.
  8. C. Milana, A. Ashta, Artificial Intelligence Techniques in Finance and Financial Markets: A Survey of the Literature, Strateg. Change 30 (2021), 189–209. https://doi.org/10.1002/jsc.2403.
  9. K. Mikkonen, M. Koskinen, C. Koskinen, et al. Qualitative Study of Social and Healthcare Educators’ Perceptions of Their Competence in Education, Health Soc. Care Community 27 (2019), 1555–1563. https://doi.org/10.1111/hsc.12827.
  10. Z. Ni, W. Chen, A Comparative Analysis of the Application of Machine Learning Algorithms and Econometric Models in Stock Market Prediction, BCP Bus. Manag. 34 (2022), 879–890. https://doi.org/10.54691/bcpbm.v34i.3108.
  11. C.M. Pierson, Supporting Ethical and Cultural Competency Development in Cross-Disciplinary Information Education in Germany, Proc. ALISE Ann. Conf. (2023). https://doi.org/10.21900/j.alise.2023.1312.
  12. H. Tian, Research on Macroeconomic Indicators and Stock Market Correlation Analysis Based on Machine Learning, Appl. Comput. Eng. 87 (2024), 179–184. https://doi.org/10.54254/2755-2721/87/20241611.
  13. N. Rohani, K. Gal, M. Gallagher, A. Manataki, Providing Insights into Health Data Science Education through Artificial Intelligence, BMC Med. Educ. 24 (2024), 564. https://doi.org/10.1186/s12909-024-05555-3.
  14. T. Wahyono, F. David, A Systematic Review of Machine Learning-Based Approaches for Financial Fraud Detection, J. Syst. Manag. Sci. 15 (2025), 69-84.
  15. A. Alsulami, R. Alabdan, Fraud Detection in Financial Transactions, Adv. Appl. Stat. 91 (2024), 969–986. https://doi.org/10.17654/0972361724052.
  16. L.K. Shrivastav, R. Kumar, An Ensemble of Random Forest Gradient Boosting Machine and Deep Learning Methods for Stock Price Prediction, J. Inf. Technol. Res. 15 (2021), 1–19. https://doi.org/10.4018/JITR.2022010102.
  17. O. Ozupek, R. Yilmaz, B. Ghasemkhani, D. Birant, R.A. Kut, A Novel Hybrid Model (EMD-TI-LSTM) for Enhanced Financial Forecasting with Machine Learning, Mathematics 12 (2024), 2794. https://doi.org/10.3390/math12172794.
  18. Q. Zhang, Y. Zhang, F. Bao, Y. Liu, C. Zhang, P. Liu, Incorporating Stock Prices and Text for Stock Movement Prediction Based on Information Fusion, Eng. Appl. Artif. Intell. 127 (2024), 107377. https://doi.org/10.1016/j.engappai.2023.107377.
  19. A. Agga, A. Abbou, M. Labbadi, Y.E. Houm, I.H. Ou Ali, CNN-LSTM: An Efficient Hybrid Deep Learning Architecture for Predicting Short-Term Photovoltaic Power Production, Electr. Power Syst. Res. 208 (2022), 107908. https://doi.org/10.1016/j.epsr.2022.107908.