Número completo
Full number
Financial Forecasting Using Deep Learning: A Comprehensive Guide
Mohamed-Amine El khayati. INREDD Research Laboratory for Innovation Responsibility and Sustainable Development, Cadi Ayyad University, Marrakesh, Morocco.
Charaf Saidi. INREDD Research Laboratory for Innovation Responsibility and Sustainable Development, Cadi Ayyad University, Marrakesh, Morocco.
Resumen/Abstract
-
Resumen / Abstract
Financial forecasting is crucial for businesses, organizations, and educational institutions as it underpins budgeting, resource allocation, and risk assessment. Traditional forecasting methods often struggle with the complexities and volatility of financial data. Deep learning, a branch of artificial intelligence utilizing neural networks, shows promise in capturing nonlinear and dynamic patterns, leading to more accurate predictions. This paper provides a step-by-step tutorial on using deep learning for financial forecasting, covering model selection, data preprocessing, training, evaluation, interpretation, and optimization. Key topics include selecting appropriate models like RNNs for sequential data, effective preprocessing techniques such as normalization and feature engineering, and strategies to avoid overfitting. The paper also explores interpretability tools like feature importance and Shapley values to enhance transparency and trust. Continuous model optimization, including hyperparameter tuning and robustness testing, is emphasized to adapt to changing data and market conditions. Implementing these strategies allows organizations to produce more accurate financial forecasts, supporting better decision-making and strategic planning in a dynamic financial environment.
Palabras Clave/Keywords
-
Palabras Clave / Keywords
Financial Forecasting, Deep Learning, Neural Networks.
Referencias/References
-
Referencias / References
[1] Abor, J.Y.: Financial Planning and Forecasting. In: Entrepreneurial Finance for MSMEs, pp. 199–224. Springer, Cham (2017).
[2] Nabar, O., Shroff, G.: Conservative Predictions on Noisy Financial Data. In: 4th ACM International Conference on AI in Finance, pp. 427–435. ACM, New York (2023).
[3] Chhabra, M., Hassan, R., Shah, M.A., Sharma, R.: A Bibliometric Review of Research on Entrepreneurial Capacity for the Period 1979 to 2022: Current Status, Development, and Future Research Directions. Cogent Business & Management 10(1) (2023).
[4] Verma, M., Srivastava, S.: On Comparing the Performance of Deep Learning Tech- niques for Modeling of Non-Linear Systems. In: 2021 International Conference on Sys- tem, Computation, Automation and Networking (ICSCAN), pp. 1–6. IEEE (2021).
[5] Haksever, Ö., Pazarçeviren, S.Y.: İşletmelerde Stratejik Planlama ve Bütçeleme ile Fi- nansal Modelleme Uygulama Örneği. İşletme 5(1), 1–23 (2024).
[6] You, Y.: Forecasting Stock Price: A Deep Learning Approach with LSTM and Hyperpa- rameter Optimization. Highlights in Science, Engineering and Technology 85, 328–338 (2024).
[7] Saracik, Ö., İncekirik, A.: Stock Price Forecasting with Deep Learning Techniques. Al- phanumeric Journal 11(2), 137–156 (2023).
[8] Kafila, Raj, R., Pavithra, P., Baloch, S.M., Adhav, S., Suneetha, S.: Advanced Use of Blockchain and Deep Learning Technologies for Financial Forecasting. In: 2023 6th International Conference on Contemporary Computing and Informatics (IC3I), pp. 2253–2257. IEEE (2023).
[9] Sukestiyarno, Y.L., Wiyanti, D.T., Azizah, L., Widada, W., Umam, K., Nugroho, Z.: Algorithm Optimizer in GA-LSTM for Stock Price Forecasting. (2024).
[10] Zhang, G.: Synergistic Advantages of Deep Learning and Reinforcement Learning in Economic Forecasting. International Journal of Global Economics and Management 1(1), 89–95 (2023).
Cómo citar/How to cite
-
Cómo citar / How to cite
El khayati, M. A., y Saidi, C. (2024). Financial Forecasting Using Deep Learning: A Comprehensive Guide. En C. Rusu et al., (1ª ed.), Transformación digital en la educación: innovaciones y desafíos desde los campus virtuales (pp. 69-73). Huelva (España): United Academic Journals (UA Journals). https://doi.org/10.54988/uaj.000027.012
