<![CDATA[Abalone (Haliotis spp.), known as "kerang mata tujuh" in Indonesia, is a highly valuable marine commodity widely sought after in the premium culinary sector, yet its quality classification is still commonly performed manually and inefficiently. This study aims to develop a market category recommendation system for abalone (Premium, Regular, Reject) based on data mining to assist in quality assessment in an automated, objective, and accurate manner. The methods used include data segmentation with the K-Means algorithm based on the physical characteristics of abalone, then classification using Decision Tree to determine market categories. The dataset comes from the UCI Machine Learning Repository and has gone through pre-processing stages such as normalization, label encoding, and outlier handling before model training. The results show that the built classification system can predict market categories with 99% accuracy, along with high precision, recall, and F1-scores across all classes, indicating the system's strong potential for implementation in the fisheries industry to support fast, data-driven decision-making. This study combines K-Means segmentation and Decision Tree classification to develop an automatic and accurate abalone market category assessment system to replace subjective manual processes]]>
Copyrights © 2026
