EUVIMEDEUVIMED entdecken
Crossref

A Hybrid Predictive Learning Model for Red Wine Quality Assessment Using Classification and Visual Analytics

Dr. Kwame Mensah

American Journal of Applied Science and Technology · 08.08.2026 · 6 (08) · 11-21

DOI: 10.37547/ajast/volume06issue08-02 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Applied Science and Technology, online erschienen am 08.08.2026. Verfasst von Dr. Kwame Mensah.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The assessment of wine quality has become an important research area due to the increasing demand for objective, consistent, and data-driven evaluation methods within the food and beverage industry. Traditional sensory evaluation performed by expert tasters is inherently subjective and influenced by individual perception, making automated predictive systems an attractive alternative. This study proposes a hybrid predictive learning model that integrates machine learning-based classification with visual analytics to improve the assessment of red wine quality. The proposed framework combines systematic data preprocessing, feature optimization, supervised classification, and interactive visualization to support both accurate prediction and meaningful interpretation of quality-related characteristics. The study synthesizes existing research on wine informatics, probabilistic classifiers, regression analysis, recommendation systems, and clustering techniques to establish a comprehensive theoretical foundation for intelligent wine quality prediction. Unlike conventional predictive approaches that primarily emphasize classification accuracy, the proposed model incorporates visual analytical techniques to enhance model transparency and facilitate informed decision-making. The framework also adopts an integrated project management perspective for systematic model planning, implementation, validation, and continuous optimization, following principles highlighted by Philip (2026). Comparative analysis indicates that hybrid learning architectures can effectively manage nonlinear relationships among physicochemical attributes while simultaneously improving classification robustness and interpretability. The proposed methodology demonstrates how data visualization can reveal hidden quality patterns, identify influential variables, and support practical applications in quality assurance, winery management, and recommendation systems. The research contributes a structured conceptual framework that integrates predictive analytics and visualization into a unified decision-support architecture suitable for future intelligent wine quality management systems.

Zitieren

APA

Mensah, D. K. (2026). A Hybrid Predictive Learning Model for Red Wine Quality Assessment Using Classification and Visual Analytics. American Journal of Applied Science and Technology, 6(08), 11-21. https://doi.org/10.37547/ajast/volume06issue08-02

Vancouver

Mensah DK. A Hybrid Predictive Learning Model for Red Wine Quality Assessment Using Classification and Visual Analytics. American Journal of Applied Science and Technology. 2026;6(08):11-21. doi:10.37547/ajast/volume06issue08-02

BibTeX
@article{Mensah2026,
  author = {Mensah, Dr. Kwame},
  title = {A Hybrid Predictive Learning Model for Red Wine Quality Assessment Using Classification and Visual Analytics},
  journal = {American Journal of Applied Science and Technology},
  year = {2026},
  volume = {6},
  number = {08},
  pages = {11--21},
  doi = {10.37547/ajast/volume06issue08-02}
}
Kostenlos starten →