arbiter
JournalsAccount

A Gannet-Optimized Discrete Hidden Markov Framework for Investment Support Systems

Yicheng Wei et al.

Journal of Organizational and End User Computing2026https://doi.org/10.4018/joeuc.402744article
AJG 1ABDC B
Weight
0.50

Abstract

Organizations operate under fixed budgets, yet latent market regimes dictate shifting capital and risk limits. Dynamically labeling these regimes from public prices is therefore critical. However, the task is discrete and poorly served by continuous models. The authors employ discrete hidden Markov models (DHMMs) to infer categorical states from continuous price series. On the other hand, real-world data are non-stationary and noisy, and the traditional Baum-Welch routine often stalls in local optima, inflating runtime and causing overfitting. To overcome these limitations, they introduce GOA-DHMM, the first adaptation of the Gannet Optimization Algorithm to DHMMs. Hybrid encoding plus temporal regularization enforces probability-simplex constraints while preserving sequential coherence. Evaluated on 1,100 days of CSI-300 data, GOA-DHMM outperforms BW, PSO, and GA in accuracy and stability, delivering clearer, faster regime signals that let organizations allocate capital and hedge risk with confidence.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.4018/joeuc.402744

Or copy a formatted citation

@article{yicheng2026,
  title        = {{A Gannet-Optimized Discrete Hidden Markov Framework for Investment Support Systems}},
  author       = {Yicheng Wei et al.},
  journal      = {Journal of Organizational and End User Computing},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.4018/joeuc.402744},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

A Gannet-Optimized Discrete Hidden Markov Framework for Investment Support Systems

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.