AI-Driven Predictive Analytics for Strategic Decision-Making in Dynamic Business Environments
DOI:
https://doi.org/10.63503/j.ijaimd.2025.166Keywords:
Artificial Intelligence (AI), Predictive Analytics, Strategic Decision-Making, Deep Learning, ROI, CNN-LSTM, TransformersAbstract
Digital transformation exposes organisations to increasingly turbulent and dynamic business environments where the broad-based approaches to decision making that were once viable in periods of certitude cannot succeed. In order to overcome this challenge, the current paper will propose an AI predictive analytics framework that will be able to improve strategic decision-making in the workplace in dynamic ecosystems. The framework integrates both multi-source (financial indicators, customer sentiment, supply chain measures, and operational performance measures) and real-time data integration, depending on machine learning (ML) and deep learning (DL) models. Since the suggested system will be in a better position to endure the changes, compared to the old-fashioned approaches, which employed the generic model and the past tendencies, the suggested system will support the adaptive learning that will filter the prediction, as the market is shifting, and will enable the system to resist the changes. Its approach is a hybrid of time-series prediction, Transformer-based architecture, and hybrid CNN-LSTM networks that can be used to recognize both time-varying and contextual associations in diverse streams of information. The decision-support metrics (predictive accuracy, decision latency and return on investment) are modelled using mathematical modelling and optimisation. Relative simulations indicate that the proposed approach is 11.6 percent predictive, 23 percent decision time shorter, and 17 percent higher ROI than the baselines with Random Forest and Logistic Regression. The market shock dynamic tests, the breakages in the supply chains, all promise that when the traditional models are brought down to a bare minimum, the structure is brought back to performance. The proposed system demonstrates that AI-based predictive analytics can be viewed as transformative due to its ability to make decisions faster, more accurately, and strategically oriented. This work develops the idea of adaptive AI models as the basis of a competitive advantage that may help a business survive in an environment of uncertainty and seize opportunities.
References
[1] Mohanta, B., Nanda, P., & Patnaik, S. (2019). Management of VUCA (Volatility, Uncertainty, Complexity and Ambiguity) Using machine learning techniques in industry 4.0 paradigm. In New Paradigm of Industry 4.0: Internet of Things, Big Data & Cyber Physical Systems (pp. 1-24). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-25778-1_1
[2] Brunner, D., Legat, C., & Seebacher, U. (2024). Towards Next Generation Data-Driven Management: Leveraging Predictive Swarm Intelligence to Reason and Predict Market Dynamics. In Collective Intelligence (pp. 152-203). CRC Press. https://doi.org/10.1201/9781032690711
[3] McCarthy, R. V., McCarthy, M. M., Ceccucci, W., Halawi, L., McCarthy, R. V., McCarthy, M. M., ... & Halawi, L. (2022). Applying predictive analytics (pp. 89-121). Springer International Publishing. https://doi.org/10.1007/978-3-030-83070-0
[4] Sharma, A. K., Sharma, D. M., Purohit, N., Rout, S. K., & Sharma, S. A. (2022). Analytics techniques: descriptive analytics, predictive analytics, and prescriptive analytics. In Decision intelligence analytics and the implementation of strategic business management (pp. 1-14). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-82763-2_1
[5] Mian, S. M., Khan, M. S., Shawez, M., & Kaur, A. (2024, July). Artificial intelligence (AI), machine learning (ML) & deep learning (DL): A comprehensive overview on techniques, applications and research directions. In 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS) (pp. 1404-1409). IEEE. doi: 10.1109/ICSCSS60660.2024.10625198.
[6] Bhogade, V., & Nithya, B. (2024). Time series forecasting using transformer neural network. International Journal of Computers and Applications, 46(10), 880-888. https://doi.org/10.1080/1206212X.2024.2396321
[7] Khalil, F., & Pipa, G. (2022). Is deep-learning and natural language processing transcending the financial forecasting? Investigation through lens of news analytic process. Computational Economics, 60(1), 147-171. https://doi.org/10.1007/s10614-021-10145-2
[8] Liu, Y. (2025, May). Hybrid Residual-Gated Recurrent Unit Framework for Enterprise Financial Distress Prediction. In 2025 3rd International Conference on Data Science and Information System (ICDSIS) (pp. 1-7). IEEE. doi: 10.1109/ICDSIS65355.2025.11070347.
[9] Gillioz, A., Casas, J., Mugellini, E., & Abou Khaled, O. (2020, September). Overview of the Transformer-based Models for NLP Tasks. In 2020 15th Conference on computer science and information systems (FedCSIS) (pp. 179-183). IEEE. DOI: 10.15439/2020F20
[10] Sharma, A., Goyal, D., & Mohana, R. (2024). An ensemble learning-based framework for breast cancer prediction. Decision Analytics Journal, 10, 100372. https://doi.org/10.1016/j.dajour.2023.100372
[11] Wong, L. W., Tan, G. W. H., Ooi, K. B., Lin, B., & Dwivedi, Y. K. (2024). Artificial intelligence-driven risk management for enhancing supply chain agility: A deep-learning-based dual-stage PLS-SEM-ANN analysis. International Journal of Production Research, 62(15), 5535-5555. https://doi.org/10.1080/00207543.2022.2063089
[12] Gude, J. A., Mitchell, M. S., Ausband, D. E., Sime, C. A., & Bangs, E. E. (2009). Internal validation of predictive logistic regression models for decision‐making in wildlife management. Wildlife biology, 15(4), 352-369. https://doi.org/10.2981/08-057
[13] Sirisha, U. M., Belavagi, M. C., & Attigeri, G. (2022). Profit prediction using ARIMA, SARIMA and LSTM models in time series forecasting: A comparison. Ieee Access, 10, 124715-124727. doi: 10.1109/ACCESS.2022.3224938.
[14] Sahin, E. K. (2020). Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest. SN Applied Sciences, 2(7), 1308. https://doi.org/10.1007/s42452-020-3060-1
[15] Deng, Y., Wang, L., Jia, H., Tong, X., & Li, F. (2019). A sequence-to-sequence deep learning architecture based on bidirectional GRU for type recognition and time location of combined power quality disturbance. IEEE Transactions on Industrial Informatics, 15(8), 4481-4493. doi: 10.1109/TII.2019.2895054.
[16] Chen, R., Wang, X., Zhang, W., Zhu, X., Li, A., & Yang, C. (2019). A hybrid CNN-LSTM model for typhoon formation forecasting. GeoInformatica, 23(3), 375-396. https://doi.org/10.1007/s10707-019-00355-0
[17] Ahmed, S., Nielsen, I. E., Tripathi, A., Siddiqui, S., Ramachandran, R. P., & Rasool, G. (2023). Transformers in time-series analysis: A tutorial. Circuits, Systems, and Signal Processing, 42(12), 7433-7466. https://doi.org/10.1007/s00034-023-02454-8
[18] Mahbooba, B., Timilsina, M., Sahal, R., & Serrano, M. (2021). Explainable artificial intelligence (XAI) to enhance trust management in intrusion detection systems using decision tree model. Complexity, 2021(1), 6634811. https://doi.org/10.1155/2021/6634811
[19] Shan, Z., & Wang, Y. (2024). Strategic talent development in the knowledge economy: a comparative analysis of global practices. Journal of the Knowledge Economy, 15(4), 19570-19596. https://doi.org/10.1007/s13132-024-01933-w
[20] Iseri, F., Iseri, H., Chrisandina, N. J., Iakovou, E., & Pistikopoulos, E. N. (2025). AI-based predictive analytics for enhancing data-driven supply chain optimization. Journal of Global Optimization, 1-28. https://doi.org/10.1007/s10898-025-01509-1
[21] Abibullaev, B., Keutayeva, A., & Zollanvari, A. (2023). Deep learning in EEG-based BCIs: A comprehensive review of transformer models, advantages, challenges, and applications. IEEe Access, 11, 127271-127301. doi: 10.1109/ACCESS.2023.3329678.
[22] Alcalá, R., Alcalá-Fdez, J., Casillas, J., Cordón, O., & Herrera, F. (2006). Hybrid learning models to get the interpretability–accuracy trade-off in fuzzy modeling. Soft Computing, 10(9), 717-734. https://doi.org/10.1007/s00500-005-0002-1
[23] Zhao, J., Zheng, T., & Litvinov, E. (2015). A unified framework for defining and measuring flexibility in power system. IEEE Transactions on power systems, 31(1), 339-347. doi: 10.1109/TPWRS.2015.2390038.
[24] Pérez-Castillo, R., Ruiz, F., & Piattini, M. (2020). A decision-making support system for Enterprise Architecture Modelling. Decision Support Systems, 131, 113249. https://doi.org/10.1016/j.dss.2020.113249
[25] Hamid, M., Anisurrahman, & Alam, B. (2025). Quantum Machine Learning for Drug Discovery: A Systematic Review. International Journal on Computational Modelling Applications, 2(3), 01–08. https://doi.org/10.63503/j.ijcma.2025.156
[26] Ankita Ghosh, Sudip Diyasi, & Siddhartha Chatterjee. (2024). Enhancing SQL Injection Prevention: Advanced Machine Learning and LSTM-Based Techniques. International Journal on Computational Modelling Applications, 1(1), 20–31. https://doi.org/10.63503/j.ijcma.2024.16
