PREDIKSI TIKET MENGGUNAKAN LSTM PADA SISTEM GLPI

NURFAIZI, ACHMAD (2023) PREDIKSI TIKET MENGGUNAKAN LSTM PADA SISTEM GLPI. S1 thesis, Universitas Mercu Buana Bekasi.

[img]
Preview
 Text
41518310039-ACHMADNURFAIZI-01 COVER.pdf
Download (206kB) | Preview
[img]
Preview
 Text
41518310039-ACHMADNURFAIZI-02 ABSTRAK.pdf
Download (29kB) | Preview
[img] Text
41518310039-ACHMADNURFAIZI-03 BAB 1.pdf
Restricted to Registered users only
Download (30kB)
[img] Text
41518310039-ACHMADNURFAIZI-04 BAB 2.pdf
Restricted to Registered users only
Download (95kB)
[img] Text
41518310039-ACHMADNURFAIZI-05 BAB 3.pdf
Restricted to Registered users only
Download (273kB)
[img] Text
41518310039-ACHMADNURFAIZI-06 BAB 4.pdf
Restricted to Registered users only
Download (64kB)
[img] Text
41518310039-ACHMADNURFAIZI-07 BAB 5.pdf
Restricted to Registered users only
Download (62kB)
[img] Text
41518310039-ACHMADNURFAIZI-08 DAFTAR PUSTAKA.pdf
Restricted to Registered users only
Download (84kB)
[img] Text
41518310039-ACHMADNURFAIZI-09 LAMPIRAN.pdf
Restricted to Registered users only
Download (692kB)

Abstract

ABSTRAK Nama : Achmad Nurfaizi NIM : 41518310039 Program Studi : Teknik Informatika Judul Laporan Skripsi : Prediksi Tiket Menggunakan LSTM Pada Sistem GLPI Pembimbing : Muhaimin Hasanudin, S.T., M.Kom GLPI (Gestionnaire Libre de Parc Informatique) merupakan suatu perangkat lunak untuk manajemen aset, dengan tambahan antar muka untuk pengajuan permintaan dan pelaporan insiden kepada teknisi komputer dalam bentuk tiket. Tiket adalah sebuah karcis gangguan atau disebut juga laporan masalah yang digunakan dalam suatu organisasi untuk melacak deteksi, pelaporan, dan resolusi dari beberapa masalah, banyaknya tiket yang masuk dan belum terselesaikan berdampak kepada ketidakpastian dan ketidak stabilan yang intens ke pelanggan. Data yang digunakan bersifat data primer yakni data tiket yang didapat dari sistem glpi berbentuk data mentah, data diolah dan direkapitulasi berdasarkan harian dari tiket permintaan pelanggan. Dalam penelitian ini menggunakan model LSTM (Long short-term Memory) dengan Dataset menjadi delapan attribut dengan jumlah data 2035 record, agar kinerja data optimal maka kami menggunakan penskalaan min-max sci-kit learn untuk mentransformasi data, ekstrak fitur, dan buat model untuk diprediksi tiket. Parameter-parameter yang digunakan diantaranya batch_size = 32, epoch = 100, learning_rate = 0.001, dengan optimizer yaitu Adam. Nilai akurasi validasi (val_acc) terbaik diperoleh pada epoch ke-82 dengan nilai 9.695, nilai loss validasi (val_loss) 0.0044. hasil penelitian menunjukan bahwa permintaan tiket menaik sedangkan hasil prediksi model permintaan tiket ditahun selanjutnya menurun karena diprediksi banyak tiket permintaan dari pelanggan sudah diselesaikan oleh team. Ini jelas menunjukkan betapa bagusnya metode LSTM untuk menganalisis deret waktu dan sequential data. Kunci : Tiket, Karcis Gangguan, Pelanggan, LSTM ABSTRACT Name : Achmad Nurfaizi NIM : 41518310039 Study Program : Technical Information Title Thesis : Ticket Prediction Using LSTM on the GLPI System Counsellor : Muhaimin Hasanudin, S.T., M.Kom GLPI (Gestionnaire Libre de Parc Informatique) is a software for asset management, with additional interface for submitting requests and reporting incidents to computer technicians in the form of tickets. A ticket is a trouble ticket or also called a problem report that is used in an organization to track the detection, reporting and resolution of several problems, the large number of incoming and unresolved tickets has an impact on intense uncertainty and instability to customers. The data used is primary data, namely ticket data obtained from the GLPI system in the form of raw data, the data is processed and recapitulated on a daily basis from customer request tickets. In this study using the LSTM (Long short-term Memory) model with the Dataset into eight attributes with a total of 2035 data records, for optimal data performance we use the minmax sci-kit learn scaling to transform data, extract features, and create models for predicted ticket. The parameters used include batch_size = 32, epoch = 100, learning_rate = 0.001, with the optimizer, Adam. The best validation accuracy value (val_acc) was obtained in the 82nd epoch with a value of 9.695, a validation loss value (val_loss) of 0.0044. The results of the study show that the demand for tickets has increased, while the predicted results for the model demand for tickets in the following year have decreased because it is predicted that many ticket requests from customers have been completed by the team. This clearly shows how good the LSTM method is for analyzing time series and sequential data. Keywords : Tickets, Interference Tickets, Customers, LSTM

Item Type: Thesis (S1)
Call Number CD: FIK/INFO 23 007
NIM/NIDN Creators: 41518310039
Uncontrolled Keywords: Tiket, Karcis Gangguan, Pelanggan, LSTM
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: siti maisyaroh
Date Deposited: 22 Sep 2023 05:43
Last Modified: 22 Sep 2023 05:43
URI: http://repository.mercubuana.ac.id/id/eprint/81392

Actions (login required)

View Item View Item
UMB Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.