The convergence of high-frequency financial data and massive consumer datasets has necessitated a paradigmatic shift toward intelligent decision-support systems. This research provides an exhaustive investigation into the application of advanced machine learning architectures-ranging from multilayer feedforward networks to hybrid fusion models-within the dual domains of financial market forecasting and e-commerce customer retention. By synthesizing foundational theories of universal approximation with contemporary advancements in feature-weighted support vector machines and random forest algorithms, this study evaluates the efficacy of predictive models in navigating market volatility and geopolitical risks. The research further explores the "Decision Engine" concept, investigating how propensity prediction based on customer data features can revolutionize supply chain forecasting and CRM strategies. Central to the analysis is the mitigation of knowledge imbalances in AI-advised decision-making and the resolution of imbalanced training sample problems through strategic sampling techniques. The findings suggest that while neural networks provide superior approximation capabilities, their integration with metaheuristics and technical analysis is essential for achieving robust performance in emerging markets and high-volatility assets like Bitcoin. This article concludes with an extensive discussion on the future of collaborative user involvement and the strategic motives behind proactive environmental strategies in sustainable corporate development.

Predictive Analytics, Neural Networks, Financial Forecasting, Customer Retention

Aysan, A. F., Demir, E., Gozgor, G., and Lau, C. K. M. (2019). Effects of the geopolitical risks on Bitcoin returns and volatility. Research in International Business and Finance, 47:511–518.

Aysan, A. F., Demirta¸s, H. B., and Sara¸c, M. (2021). The Ascent of Bitcoin: Bibliometric Analysis of Bitcoin Research. Journal of Risk and Financial Management, 14(9):427.

Bai, S., Kolter, J. Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling.

Baker, S. R., Bloom, N., Davis, S. J., and Kost, K. J. (2019). Policy news and stock market volatility. Technical report, National Bureau of Economic Research.

Barandela, R., Valdovinos, R. M., S´anchez, J. S., and Ferri, F. J. (2004). The Imbalanced Training Sample Problem: Under or over Sampling? In Lecture Notes in Computer Science, Springer.

Boone, T., Ganeshan, R., Jain, A. and Sanders, N.R. (2019). Forecasting sales in the supply chain: Consumer analytics in the big data era. International journal of forecasting, 35(1), pp.170-180.

Boppana, V.R. (2021). Innovative CRM Strategies for Customer Retention in E-Commerce. ESP Journal of Engineering & Technology Advancements (ESP-JETA), 1(1), pp.173-183.

Campbell, C., Sands, S., Ferraro, C., Tsao, H.Y.J. and Mavrommatis, A. (2020). From data to action: How marketers can leverage AI. Business horizons, 63(2), pp.227-243.

Chaffey, D. and Smith, P.R. (2022). Digital marketing excellence: planning, optimizing and integrating online marketing. Routledge.

Chan, R.Y., Lai, J.W. and Kim, N. (2022). Strategic motives and performance implications of proactive versus reactive environmental strategies in corporate sustainable development. Business Strategy and the Environment, 31(5), pp.2127-2142.

Chang, P.-C. et al. (2009). A neural network with a case based dynamic window for stock trading prediction. Expert Systems with Applications.

Chen, A.-S. et al. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan stock index. Computers & Operations Research.

Chen, T.-l. et al. (2016). An intelligent pattern recognition model for supporting investment decisions in stock market. Information Sciences.

Chen, Y. et al. (2017). A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications.

Chopra, N., Joshi, M. and Nair, N. (2020). Enhancing Predictive Customer Retention Using Random Forest and Neural Network Algorithms in AI-Driven Models. International Journal of AI Advancements, 9(4).

Dash, R. et al. (2016). A hybrid stock trading framework integrating technical analysis with machine learning techniques. The Journal of Finance and Data Science.

Gerlein, E.A. et al. (2016). Evaluating machine learning classification for financial trading: An empirical approach. Expert Systems with Applications.

Göçken, M. et al. (2016). Integrating metaheuristics and artificial neural networks for improved stock price prediction. Expert Systems with Applications.

Gomez, C. et al. (2023). Mitigating knowledge imbalance in AI-advised decision-making through collaborative user involvement. International Journal of Human-Computer Studies.

Hassan, M.R. et al. (2007). A fusion model of HMM, ANN and GA for stock market forecasting. Expert Systems with Applications.

Henrique, B.M. et al. (2018). Stock price prediction using support vector regression on daily and up to the minute prices. The Journal of Finance and Data Science.

Henrique, B.M. et al. (2019). Literature review: Machine learning techniques applied to financial market prediction. Expert Systems with Applications.

Hornik, K. (1991). Approximation capabilities of multilayer feedforward networks. Neural Networks.

Hornik, K. et al. (1989). Multilayer feedforward networks are universal approximators. Neural Networks.

Hsu, M.-W. et al. (2016). Bridging the divide in financial market forecasting: Machine learners vs. financial economists. Expert Systems with Applications.

Krishnan, G., Bhat, A. K., & Shah, J. (2025). Decision engine: Propensity prediction in the financial industry based on customer data features. In Artificial Intelligence and Sustainable Innovation, CRC Press.