Rancang Bangun Aplikasi Berbasis Website Untuk Memprediksi Delay Keberangkatan Kapal di PT. XYZ Menggunakan K-Nearest Neighbor

Ranto, Kharin Octavian (2022) Rancang Bangun Aplikasi Berbasis Website Untuk Memprediksi Delay Keberangkatan Kapal di PT. XYZ Menggunakan K-Nearest Neighbor. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 10611810000080-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2024. Download (2MB) | Request a copy

Abstract

PT XYZ merupakan perusahaan yang memberikan layanan jasa terminal petikemas internasional dan domestik, dengan kegiatan bongkar muat diawali dari kegiatan kapal sandar hingga kapal berangkat meninggalkan dermaga. Kedatangan kapal ke PT XYZ telah dijadwalkan atau dikenal dengan istilah window. Tahun 2021 terdapat 25,68% delay keberangkatan kapal yang mengakibatkan lama sandar kapal menjadi bertambah sehingga berpengaruh terhadap rendahnya nilai Box/Ship/Hour (BSH), serta dapat mengakibatkan jadwal kapal berikutnya mengalami keterlambatan sandar. Hal ini berpengaruh terhadap pendapatan perusahaan dan menjadi fokus perhatian bagi pihak terminal untuk ditangani. Penelitian ini dilakukan dengan membuat aplikasi berbasis website dengan metode K-Nearest Neighbor untuk mengklasifikasikan delay keberangkatan kapal dengan harapan dapat membantu memberikan bahan pertimbangan kepada pihak terminal dalam menyusun jadwal sandar kapal selanjutnya dan pihak operasional dapat melakukan kegiatan antisipasi untuk mencegah delay keberangkatan kapal dari kapal yang diprediksi delay melalui pengalokasian sarana bongkar muat. Diperoleh bahwa hasil klasifikasi menggunakan metode KNN paling baik diterapkan pada proporsi pembagian data training 80% dan data testing 20% serta k = 5 dengan nilai akurasi sebesar 91% dan presisi > 90%, namun untuk kategori delay ≤ 4 jam dan > 4 jam memiliki nilai sensitifitas ≤ 50%, berarti kapal dengan kategori delay ≤ 4 jam dan > 4 jam hasil prediksinya kurang tepat. Aplikasi prediksi delay keberangkatan berbasis website berisi form input data untuk melakukan prediksi terhadap delay keberangkatan kapal.
====================================================================================================================================
PT XYZ is a company that provides international and domestic container terminal services, with loading and unloading activities starting from ship docking activities until the ship departs from the dock. The arrival of the ship to PT XYZ has been scheduled or known as the window. In 2021 there are 25.68% delay in ship departures, which will increase the length of the ship's berth, which will affect the low value of Box/Ship/Hour (BSH) and may cause the next ship's schedule to experience delay berthing. This affects the company's revenue and becomes the focus of attention for the terminal to be handled. This research was conducted by creating a website-based application with the K-Nearest Neighbor method to classify ship departure delays in the hope that it can help provide consideration to the terminal in compiling the next ship docking schedule and the operational department can carry out anticipatory activities to prevent ship departure delays from ships that are predicted to be delayed through the allocation of loading and unloading facilities. It was found that the results of the classification using the KNN method were best applied to the proportion of distribution of 80% training data and 20% testing data and k = 5 with an accuracy value of 91% and precision > 90%, but for the category of delay ≤ 4 hours and > 4 hours has a sensitivity value ≤ 50%, this means that ships with a delay category of 4 hours and > 4 hours have inaccurate predictions. The website-based delay departure application contains a data input form to predict ship departure delays.

Item Type:	Thesis (Other)
Additional Information:	RSSB 519.53 Ran r-1 2022
Uncontrolled Keywords:	Bongkar Muat, Delay, K-Nearest Neighbor, Klasifikasi, Prediksi
Subjects:	Q Science > QA Mathematics > QA278.55 Cluster analysis
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	- Davi Wah
Date Deposited:	17 Nov 2023 07:48
Last Modified:	17 Nov 2023 07:48
URI:	http://repository.its.ac.id/id/eprint/105125

Actions (login required)

View Item