Pemanfaatan Machine Learning Untuk Prediksi Target Tambah Daya Listrik Pelanggan Prabayar (Studi Kasus : Pt Pln Ulp Watang Sawitto)

Afthoni, Rizqa (2022) Pemanfaatan Machine Learning Untuk Prediksi Target Tambah Daya Listrik Pelanggan Prabayar (Studi Kasus : Pt Pln Ulp Watang Sawitto). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032201120-Master_Thesis.pdf Restricted to Repository staff only Download (2MB)

Abstract

Perkembangan teknologi sistem informasi dan ilmu pengetahuan khususnya dalam bidang pemasaran membuat para pelaku usaha berupaya untuk meningkatkan competitive advantage mereka dengan mengerahkan sumber daya yang dimiliki oleh perusahaan. Perusahaan dituntut untuk berinovasi dalam mengelola perusahaannya agar dapat bertahan dalam dunia persaingan. Mampu memprediksi pelanggan prabayar yang berpotensi tambah daya listrik merupakan salah satu strategi pendukung untuk keberhasilan program pemasaran tambah daya pelanggan berdasarkan karakteristik konsumsi listriknya. Dalam penelitian ini, data yang digunakan adalah data pelanggan prabayar tarif rumah tangga dengan variabel Daya listrik pelanggan (VA), Frekuensi beli token listrik per tahun, Total pemakaian kWh per tahun, Total Rupiah pembelian token per tahun, selisih daya VA pelanggan, Jam nyala, periode hari pembelian token listrik, dan histori tambah daya listrik pelanggan. Data-data tersebut, selanjutnya diproses dengan menggunakan algoritma Machine Learning, yaitu unsupervised learning dan supervised learning. Pengolahan unsupervised learning mempunyai tujuan untuk mengelompokkan clustering pelanggan prabayar terlebih dahulu berdasarkan kemiripan karakteristik konsumsi listriknya, setelah didapatkan jumlah klasternya, maka langkah selanjutnya adalah menentukan target pemasaran tambah daya pelanggan prabayar berdasarkan algoritma supervised learning. Metode unsupervised learning yang digunakan dalam penelitian ini adalah metode K-means untuk klustering pelanggan prabayar nya, lalu dilanjutkan dengan metode supervised learning yaitu Artificial Neural Netwotk dan Gradient Boosted untuk menentukan target pelanggan prabayar yang berpotensi tambah daya. Hasil dari permodelan tersebut dibandingkan mana yang lebih relevan melalui evaluasi Area Under Curve. Hasil dari pengolahan data tersebut, digunakan sebagai data pendukung pengambilan keputusan bisnis PLN.
==============================================================================================================================
The development of information system technology and science, especially in the field of marketing, makes business actors seek to increase their competitive advantage by mobilizing the resources owned by the company. Companies are required to innovate in managing their companies in order to survive in the competitive world. Being able to predict prepaid customers who have the potential to add electricity is one of the supporting strategies for the success of the marketing program for adding power to customers based on the characteristics of their electricity consumption. In this study, the data used is household tariff prepaid customer data with variable customer electric power (VA), frequency of purchasing electricity tokens per year, total consumption of kWh per year, total Rupiah purchases of tokens per year, customer VA power difference, hours of operation , the period of days of purchasing electricity tokens, and the history of adding electricity to customers. These data are then processed using Machine Learning algorithms, namely unsupervised learning and supervised learning. Unsupervised learning processing has the aim of grouping prepaid customer clustering first based on the similarity of their electricity consumption characteristics, after obtaining the number of clusters, the next step is to determine the marketing target of adding power to prepaid customers based on the supervised learning algorithm. The unsupervised learning method used in this study is the K-means method for clustering prepaid customers, then followed by supervised learning methods, namely Artificial Neural Netwotk and to Gradient Boosted determine target customers. prepaid which has the potential to add power. The results of the modeling are compared which one is more relevant through the evaluation of the Area Under Curve. The results of the data processing are used as data to support PLN's business decision making.

Item Type:	Thesis (Masters)
Additional Information:	RTMT 658.812 Aft p-1 2022
Uncontrolled Keywords:	Unsupervised Machine Learning, Supervised Machine Learning, Clistering. Unsupervised Machine Learning, Supervised Machine Learning, Clustering.
Subjects:	T Technology > T Technology (General)
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Mr. Marsudiyana -
Date Deposited:	08 Jul 2026 03:21
Last Modified:	08 Jul 2026 03:21
URI:	http://repository.its.ac.id/id/eprint/134491

Actions (login required)

View Item