Telecommunication industries are experiencing substantial problems related to the migration of customers due to a large number of competing companies, dynamic circumstances, as well as the presence of many innovative and attractive offerings. The situation has resulted in a high level of customer migration, affecting a decrement toward the company revenue. Regarding that condition, the customer churn is one well-know approach that can help in increasing the company's revenue and reputation. As to predict the reason behind the migration of customer, this study proposed a data mining classification technique by applying the C4.5 algorithm. Patterns generated by the model were implemented using 10-fold cross-validation, resulting in a model with an accuracy rate of 87%, precision 87.5%, and a recall of 97%. Based on the good performance quality of the model, it can be stated that the C4.5 algorithm succeeded to discover several causes from the migration of telecommunication users, in which price holds the top place as the primary reason
Cooperatives have purpose to prosper their members. Cooperatives are expected to play an active role in raising their standard of living. A cooperative has several types of business units in order to fulfill the purpose, for example rental business. Rental occurs because of short-term and urgent needs of consumers. Rental business has been promoted online but there are a lot of ordering phases done manually. Cooperative needs a rental marketplace application so cooperative can be more productive. This rental marketplace is a web based application and developed using Extreme Programming method which perceptive to user's need. Laravel framework with PHP programming language was used to build this application. The conclusion of this research is this system is able to facilitate the process of renting goods, providing accurate information about rental goods, and expanding the cooperative business sector.
Video profil menjadi media yang semakin banyak digunakan dalam menyampaikan informasi terkait suatu organisasi, produk, ataupun jasa, terutama di era digitalisasi seperti saat ini. Penggunaan video profil di bidang usaha industri dikenal sebagai salah satu teknik mempromosikan produk secara singkat dan efisien, serta mampu menjangkau kalangan yang lebih luas. Pekon Wonodadi merupakan desa binaan yang memiliki banyak usaha kecil dan menengah yang dibangun oleh masyarakat. Sayangnya, penjualan dan teknik promosi yang dilakukan oleh pelaku usaha Pekon Wonodadi masih secara konvensional dan terbatas. Kegiatan pengabdian kepada masyarakat ini memberikan pelatihan kepada masyarakat di salah satu desa binaan Universitas Lampung, yaitu Pekon Wonodadi, terkait pembuatan video profil usaha kecil dan menengah menggunakan Filmora 9. Kegiatan pelatihan yang dilaksanakan dalam kurun waktu 6 bulan telah berhasil meningkatkan pengetahuan pelaku usaha Pekon Wonodadi serta membantu mereka untuk dapat memperluas promosi produknya dengan pengembangan video yang dapat diunggah di media sosial maupun situs lainnya.
Carrasius Auratus atau dikenal sebagai ikan Maskoki adalah ikan hias yang paling banyak dipelihara didalam akuarium yang memiliki spesies, bentuk, dan warna yang beragam. Identifikasi ikan Maskoki secara manual sulit dilakukan. Hal ini disebabkan anatomi ikan Maskoki yang hampir serupa. Spesies yang anatominya hampir serupa diperlukan identifikasi ikan secara otomatis. Identifikasi ikan Maskoki memiliki beberapa proses untuk menentukan tingkat keberhasilan. Salah satu proses yang sangat penting untuk identifikasi yaitu segmentasi. Segmentasi merupakan tahapan untuk memisahkan antara objek dan background. Hasil segmentasi yang baik akan memberikan hasil ekstraksi fitur yang maksimal dan pasti berdampak pada hasil identifikasi yang optimal. Penelitian ini bertujuan membuat sebuah sistem yang dapat digunakan untuk segmentasi objek ikan Maskoki dengan background menggunakan metode Expectation Maximization. Expectation Maximization adalah algoritma untuk menduga suatu parameter dalam suatu fungsi dengan menggunakan Maximum Likelihood Estimation (MLE). Spesies ikan Maskoki masing-masing berjumlah 72 citra total keseluruhan berjumlah 216. Hasil evaluasi segmentasi ikan Maskoki menggunakan metode Expectation Maximization mampu bekerja baik dengan tingkat akurasi mencapai 89,14%. Analisis hasil segmentasi citra ikan yang tidak sempurna dipengaruhi oleh cahaya putih dan warna background hampir serupa dengan objek ikan Maskoki. Hasil segmentasi citra ikan Maskoki terbaik dipengaruhi oleh citra ikan Maskoki yang baik pada saat proses pengambilan citra pada saat screenshot memiliki fokus yang stabil dan tidak blur, sehingga menghasilkan tepian objek ikan Maskoki terlihat jelas dan tajam.
KKN is an intracurricular activity that provides learning and work experience to students in community development activities. The Implementation Board of the Real Work Program (BP-KKN) of the University of Lampung made the information system an important component in the implementation of KKN. BP-KKN's success in carrying out its duties depends on the extent to which the KKN information system management has been implemented. The use of the KKN information system raises various risks that can interfere with the implementation of KKN and cause losses both non-material and material to BP-KKN. BP-KKN needs to apply risk management to reduce the risks that arise, so that the problems caused do not result in the use of KKN information systems being hampered. The method used is NIST 800-30 which is an information system risk management framework with three stages, namely risk assessment, risk mitigation, and risk evaluation. KKN has 9 risks that can interfere with the sustainability of the information system. The final result of the KKN information system risk management is in the form of recommendations given to reduce the risk that will occur in the information system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.