Towards Intelligent Investment Risk Modeling: Probabilistic Reasoning and Adaptive Decision Systems Under Uncertainty
- 1Finance-Accounting Department, Faculty of Economic Sciences, Lucian Blaga University of Sibiu, 550024 Sibiu, Romania
Abstract
Investment risk modeling remains challenging due to uncertainty, structural change, and market dynamics. This study develops an integrated empirical framework linking adaptive Bayesian forecasting, predictive-uncertainty evaluation, and risk-sensitive portfolio decision-making in a five-asset system comprising Microsoft, NVIDIA, Tesla, IBM, and Boeing. The TVP-VAR is employed as an established adaptive forecasting component and evaluated against expanding-mean and fixed-parameter VAR benchmarks using point-forecast accuracy, probabilistic calibration, regime-specific performance, and investment outcomes. Results show that the TVP-VAR does not systematically outperform simpler benchmarks in one-step-ahead point forecasting. However, it produces higher mean log scores and 95% predictive-interval coverage closer to nominal levels across all five assets, although these improvements generally require wider intervals and do not yield superior CRPS values. Sensitivity analysis shows that the strongest model-based portfolio performance occurs at λ = 1, where forgetting-factor-driven coefficient variation is eliminated while adaptive covariance updating remains active. Nevertheless, the equal-weight portfolio delivers the strongest overall risk-adjusted performance. Comparison with static covariance indicates that the economic advantage of adaptive covariance estimation is modest and criterion-dependent. Greater parameter adaptivity does not imply universal statistical or economic superiority; its value is more evident in predictive-uncertainty representation and calibration than in consistently improved point forecasts or portfolio outcomes.
Related
- Robust optimal reinsurance and ESG investment under rating-innovation ambiguity and ESG rating uncertainty
- Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
- Volatility-Corrected Prediction Intervals: Locally Adaptive Uncertainty Quantification for Probabilistic Time-Series Forecasting
- A Probabilistic Modeling Framework for Transient Debris Outcomes in Low Lunar Orbits
- Spatio-temporal Latent Denoising Diffusion Probabilistic Models for Reduced-order Modeling of Parametrized Dynamical Systems
BibTeX
@article{moldovan2026towards,
title = {{Towards Intelligent Investment Risk Modeling: Probabilistic Reasoning and Adaptive Decision Systems Under Uncertainty}},
author = {Radu-Anton Moldovan and Marian Pompiliu Cristescu},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14203812},
url = {https://www.mdpi.com/2227-7390/14/20/3812},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Towards Intelligent Investment Risk Modeling: Probabilistic Reasoning and Adaptive Decision Systems Under Uncertainty
AU - Radu-Anton Moldovan
AU - Marian Pompiliu Cristescu
PY - 2026
DA - 2026/10/20
JO - Mathematics
DO - 10.3390/math14203812
UR - https://www.mdpi.com/2227-7390/14/20/3812
AB - Investment risk modeling remains challenging due to uncertainty, structural change, and market dynamics. This study develops an integrated empirical framework linking adaptive Bayesian forecasting, predictive-uncertainty evaluation, and risk-sensitive portfolio decision-making in a five-asset system comprising Microsoft, NVIDIA, Tesla, IBM, and Boeing. The TVP-VAR is employed as an established adaptive forecasting component and evaluated against expanding-mean and fixed-parameter VAR benchmarks using point-forecast accuracy, probabilistic calibration, regime-specific performance, and investment outcomes. Results show that the TVP-VAR does not systematically outperform simpler benchmarks in one-step-ahead point forecasting. However, it produces higher mean log scores and 95% predictive-interval coverage closer to nominal levels across all five assets, although these improvements generally require wider intervals and do not yield superior CRPS values. Sensitivity analysis shows that the strongest model-based portfolio performance occurs at λ = 1, where forgetting-factor-driven coefficient variation is eliminated while adaptive covariance updating remains active. Nevertheless, the equal-weight portfolio delivers the strongest overall risk-adjusted performance. Comparison with static covariance indicates that the economic advantage of adaptive covariance estimation is modest and criterion-dependent. Greater parameter adaptivity does not imply universal statistical or economic superiority; its value is more evident in predictive-uncertainty representation and calibration than in consistently improved point forecasts or portfolio outcomes.
SN - 2227-7390
ER -