Volume 24 , Issue 1 , PP: 136-147, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Abdelgalal O. I. Abaker 1 *
Doi: https://doi.org/10.54216/IJNS.240113
Resolving financial futures through inverse problem-solving delves into the complicated process of deciphering the difficulties subjective in the financial market to forecast behaviours and future trends. Inverse problem-solving involves working backwards from observed outcomes to uncover the underlying conditions or parameters, unlike prediction models, which often rely on past information to predict future outcomes. This method in the finance sector includes untangling the numberless factors influencing the market dynamics, like technological advancements, economic indicators, investor sentiment, and geopolitical events. Analysts can tease out hidden patterns and relationships within financial data using statistical techniques and complex mathematical algorithms, enabling them to generate accurate predictions of market volatility, asset prices, and other crucial metrics. The financial future becomes less opaque through the lens of inverse problem solving, providing policymakers and investors great foresight and insight into navigating the uncertainties of global markets. Hence, this study introduces a Neutrosophic MOOSRA with Whale Optimization Algorithm (NMOOSRA-WOA) for Unraveling Financial Futures through Inverse Problem Solving. The NMOOSRA-WOA incorporates linear scaling normalization, NMOOSRA-based prediction, and WOA-based parameter tuning to boost the robustness and accuracy of financial predictions. The NMOOSRA technique generates predictions based on past financial time series data. Moreover, the framework integrates the Whale Optimization Algorithm (WOA) for parameter tuning, leveraging whale pods' search abilities to optimize predictive performance and finetune model parameters. The NMOOSRA-WOA provides a comprehensive algorithm for financial prediction by synergistically combining these methodologies, which facilitates more accurate forecasts of market trends, asset prices, and other critical indicators. Experimental results on real-time financial datasets demonstrate the superiority and efficacy of the proposed framework over other classical prediction techniques, highlighting its potential for risk management within dynamic financial markets and real-time applications in investment decision-making.
Financial Market , Inverse Problem Solving , Whale Optimization Algorithm , Machine Learning , Neutrosophic MOOSRA
[1] Sajjad, S., Bhuiyan, R.A., Dwyer, R.J., Bashir, A. and Zhang, C., 2024. Balancing prosperity and sustainability: unraveling financial risks and green finance through a COP27 lens. Studies in Economics and Finance.
[2] Mohammed I. Alghamdi, A Comprehensive Analysis of Cyber Security Protection Approaches for Financial Firms: A Case of Al Rajhi Bank, Saudi Arabia, Journal of Cybersecurity and Information Management, Vol. 9 , No. 1, (2021):8-17.
[3] Zenat Mohamed,Mahmoud M. Ismail,Shereen Zaki, The Digital Revolution in Trade Finance: Exploring The Impact of Smart Blockchain-Based Letters of Credit On E-business Transactions, International Journal of Advances in Applied Computational Intelligence, vol. 3, no. 1, (2023):53-63.
[4] Huang, W., Zhao, J. and Wang, X., 2024. Model-driven multimodal LSTM-CNN for unbiased structural forecasting of European Union allowances open-high-low-close price. Energy Economics, p.107459.
[5] Kim, S., Ku, S., Chang, W. and Song, J.W., 2020. Predicting the direction of US stock prices using effective transfer entropy and machine learning techniques. IEEE Access, 8, pp.111660-111682.
[6] Ayvaz, E., Kaplan, K. and Kuncan, M., 2020. An integrated LSTM neural networks approach to sustainable, balanced scorecard-based early warning system. IEEE Access, 8, pp.37958-37966.
[7] Schlecht, I., Maurer, C. and Hirth, L., 2024. Financial contracts for differences: The problems with conventional CfDs in electricity markets and how forward contracts can help solve them. Energy Policy, 186, p.113981.
[8] Luo, J., Chen, Z. and Wang, S., 2023. Realized volatility forecast of financial futures using time-varying HAR latent factor models. Journal of Management Science and Engineering, 8(2), pp.214-243.
[9] Lin, Y., Chen, K., Zhang, X., Tan, B. and Lu, Q., 2022. Forecasting crude oil futures prices using BiLSTM-Attention-CNN model with Wavelet transform. Applied Soft Computing, 130, p.109723.
[10] Cao, Z., Guo, R., Du, W., Gao, J. and Golubnichiy, K.V., 2024, March. Optimizing Stock Option Forecasting with the Assembly of Machine Learning Models and Improved Trading Strategies. In Future of Information and Communication Conference (pp. 610-620). Cham: Springer Nature Switzerland.
[11] Kim, S., Yun, S.B., Bae, H.O., Lee, M. and Hong, Y., 2024. Physics-informed convolutional transformer for predicting volatility surface. Quantitative Finance, 24(2), pp.203-220.
[12] Cao, Z., Du, W. and Golubnichiy, K.V., 2023, July. Application of Convolutional Neural Networks with Quasi-Reversibility Method Results for Option Forecasting. In Science and Information Conference (pp. 761-770). Cham: Springer Nature Switzerland.
[13] Chen, L., Gallet, A., Huang, S.S., Liu, D. and Smyl, D., 2022. Probabilistic cracking prediction via deep learned electrical tomography. Structural Health Monitoring, 21(4), pp.1574-1589.
[14] Tang, P., Tang, T. and Lu, C., 2024. Predicting systemic financial risk with interpretable machine learning. The North American Journal of Economics and Finance, 71, p.102088.
[15] Zhang, X., Yang, K., Lu, Q., Wu, J., Yu, L. and Lin, Y., 2023. Predicting carbon futures prices based on a new hybrid machine learning: Comparative study of carbon prices in different periods. Journal of Environmental Management, 346, p.118962.
[16] Wang, J. and Liu, J., 2024. Two-Stage Deep Ensemble Paradigm Based on Optimal Multi-scale Decomposition and Multi-factor Analysis for Stock Price Prediction. Cognitive Computation, 16(1), pp.243-264.
[17] Yang, F., Chen, J. and Liu, Y., 2023. Improved and optimized recurrent neural network based on PSO and its application in stock price prediction. Soft computing, 27(6), pp.3461-3476.
[18] Ajay, D., Aldring, J., Abirami, S. and Jeni Seles Martina, D., 2020. A SVTrN-number approach of multi-objective optimization on the basis of simple ratio analysis based on MCDM method. International Journal of Neutrosophic Science, 5(1), pp.16-28.
[19] Karadeniz, A.T., Başaran, E. and Çelik, Y., 2024. Classification of walnut dataset by selecting CNN features with whale optimization algorithm. Multimedia Tools and Applications, pp.1-16.
