<![CDATA[The ornamental fish farming industry requires consistent water quality management, yet PT Ikan Bangun Indonesia still relies on manual expert judgment to determine fish-water compatibility, making the process subjective and prone to delayed detection of critical conditions. This research develops a web-based decision support system that combines a Rule-Based System using Forward Chaining as a lethal-condition filter (Layer I) with a K-Nearest Neighbor algorithm based on Euclidean distance as a suitability ranking layer (Layer II), covering ten ornamental fish species and seven water quality parameters. The system was built using a three-tier architecture with React.js, Laravel, PostgreSQL, and a Python FastAPI microservice, and was evaluated through Black Box Testing, White Box Testing using basis path testing, and a Confusion Matrix approach. The results show that all functional scenarios passed testing, all internal logical paths executed correctly, and the hybrid model classified water feasibility with 100% accuracy, precision, and recall. This study concludes that the hybrid Rule-Based and KNN approach is effective and reliable for automated decision-making in ornamental fish aquaculture]]>
Copyrights © 2026
