Sistem Informasi Prediksi Timeline Pembuatan Kapal menggunakan Algoritma Multiple Linear Regression

Abstract

Ship construction duration estimation at PT Karimun Marine Shipyard still relies heavily on staff experience and subjective judgment, resulting in inconsistent estimates across projects and limited use of historical data as a basis for calculation. This research aims to design and develop a web-based information system to predict ship construction timelines using the Multiple Linear Regression algorithm, with predictor variables comprising ship type, length overall (LOA), width, height, and Gross Tonnage (GT). The system was developed using the Prototype method and built with the Laravel framework, Python for machine learning modeling, and MySQL as the database. The resulting system integrates ship data management, historical data, model training and evaluation, and timeline prediction within a single web application, thereby assisting Quality Control staff and planning personnel in determining project completion duration more objectively and efficiently.