View in EDS

Developing a Dashboard Embedded with KNN Machine Learning Algorithm for Wine Quality Prediction

Saved in:
Bibliographic Details
Title: Developing a Dashboard Embedded with KNN Machine Learning Algorithm for Wine Quality Prediction
Authors: Theophilus Bamise Ajala, Rashid Kehinde Oloko, Abiodun Richard Agboola
Source: International Journal of Innovative Science and Research Technology. :1096-1103
Publisher Information: International Journal of Innovative Science and Research Technology, 2025.
Publication Year: 2025
Description: In the beverage sector, wine quality is crucial because of its high demand and competitive market. Classifying wine quality is a challenging task because the evaluation provided by human specialists is costly and time-consuming. The aim of this research is to develop a dashboard embedded with KNN machine learning algorithm for wine quality prediction. The user opens the GUI application, supplies the values of the wine features, the entered information serves as the dataset for the red wine quality prediction system, which utilizes it to accurately forecast outcomes based on the specified range. The output of the KNN algorithm has been estimated using various evaluation metrics. with respect to precision, recall, f1-score and accuracy are 21.277%, 52.632%, 30.303%, and 85.625% respectively. Kaggle red wine dataset serves as a benchmark for the research. The essence of this research is that the adoption of a machine learning algorithm in predicting wine quality can enhance both the efficiency and precision of wine quality evaluations before production.
Document Type: Article
Language: English
DOI: 10.38124/ijisrt/25nov409
Accession Number: edsair.doi...........6611b3379a7658deee2e5172fbcc033f
Database: OpenAIRE
Description
Abstract:In the beverage sector, wine quality is crucial because of its high demand and competitive market. Classifying wine quality is a challenging task because the evaluation provided by human specialists is costly and time-consuming. The aim of this research is to develop a dashboard embedded with KNN machine learning algorithm for wine quality prediction. The user opens the GUI application, supplies the values of the wine features, the entered information serves as the dataset for the red wine quality prediction system, which utilizes it to accurately forecast outcomes based on the specified range. The output of the KNN algorithm has been estimated using various evaluation metrics. with respect to precision, recall, f1-score and accuracy are 21.277%, 52.632%, 30.303%, and 85.625% respectively. Kaggle red wine dataset serves as a benchmark for the research. The essence of this research is that the adoption of a machine learning algorithm in predicting wine quality can enhance both the efficiency and precision of wine quality evaluations before production.
DOI:10.38124/ijisrt/25nov409