Developing an Artificial Intelligence-Based Investment Decision-Support Model for Portfolio Management Under Severe Market Volatility
Keywords:
Artificial intelligence, investment decision support, portfolio management, severe market volatility, machine learning, risk control, thematic analysisAbstract
This study aimed to develop an artificial intelligence-based investment decision-support model for portfolio management under severe market volatility, with emphasis on risk prediction, adaptive asset allocation, tail-risk control, and explainability of algorithmic investment decisions. This study adopted a qualitative exploratory design. The participants consisted of 22 experts from Tehran, including portfolio managers, investment analysts, financial risk specialists, fintech professionals, capital market experts, and university academics. Participants were selected using purposive and criterion-based sampling. Data were collected through semi-structured interviews and the interview process continued until theoretical saturation was achieved. Saturation occurred at the nineteenth interview, followed by three confirmatory interviews to ensure the stability and adequacy of the extracted categories. Data were analyzed using thematic analysis with the support of NVivo software. Trustworthiness was enhanced through member checking, peer review, audit trail, and continuous comparison of codes and categories. The analysis resulted in five main categories: “multi-source data integration and market regime detection,” “intelligent prediction of risk and return under severe volatility,” “adaptive portfolio optimization and tail-risk control,” “explainability, trust, and human oversight,” and “data governance, operational infrastructure, and algorithmic error control.” The findings indicated that an effective AI-based investment decision-support model should not be limited to price forecasting. Rather, it should operate as a multi-layered system capable of processing historical market data, behavioral data, macroeconomic indicators, news, market sentiment, liquidity conditions, and investor-specific risk constraints simultaneously. The results suggest that an AI-based investment decision-support system is effective under turbulent market conditions only when it balances algorithmic accuracy, interpretability, risk control, adaptability to market regime shifts, and human judgment. The proposed model can serve as a practical framework for asset management companies, investment funds, brokerage firms, and financial institutions seeking to design intelligent portfolio management systems in highly volatile markets.
Downloads
References
Ang, A. (2014). Asset management: A systematic approach to factor investing. Oxford University Press.
Arner, D. W., Barberis, J., & Buckley, R. P. (2017). FinTech, RegTech, and the reconceptualization of financial regulation. Northwestern Journal of International Law & Business, 37(3), 371–414.
Bertsimas, D., & Kallus, N. (2020). From predictive to prescriptive analytics. Management Science, 66(3), 1025–1044. https://doi.org/10.1287/mnsc.2018.3253
Black, F., & Litterman, R. (1992). Global portfolio optimization. Financial Analysts Journal, 48(5), 28–43. https://doi.org/10.2469/faj.v48.n5.28
Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Creswell, J. W., & Poth, C. N. (2018). Qualitative inquiry and research design: Choosing among five approaches (4th ed.). Sage.
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv. https://arxiv.org/abs/1702.08608
Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of variance of United Kingdom inflation. Econometrica, 50(4), 987–1007. https://doi.org/10.2307/1912773
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009
Guest, G., Bunce, A., & Johnson, L. (2006). How many interviews are enough? An experiment with data saturation and variability. Field Methods, 18(1), 59–82. https://doi.org/10.1177/1525822X05279903
Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: Deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3–12. https://doi.org/10.1002/asmb.2209
Jiang, Z., Xu, D., & Liang, J. (2017). A deep reinforcement learning framework for the financial portfolio management problem. arXiv. https://arxiv.org/abs/1706.10059
Jorion, P. (2007). Value at risk: The new benchmark for managing financial risk (3rd ed.). McGraw-Hill.
Kritzman, M., & Li, Y. (2010). Skulls, financial turbulence, and risk management. Financial Analysts Journal, 66(5), 30–41. https://doi.org/10.2469/faj.v66.n5.3
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. Sage.
López de Prado, M. (2018). Advances in financial machine learning. Wiley.
Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91. https://doi.org/10.1111/j.1540-6261.1952.tb01525.x
Molnar, C. (2022). Interpretable machine learning: A guide for making black box models explainable (2nd ed.). https://christophm.github.io/interpretable-ml-book/
Rockafellar, R. T., & Uryasev, S. (2000). Optimization of conditional value-at-risk. The Journal of Risk, 2(3), 21–41. https://doi.org/10.21314/JOR.2000.038
Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance, 19(3), 425–442. https://doi.org/10.1111/j.1540-6261.1964.tb02865.x
