Implementasi Deep Learning Dengan Metode Long Short-Term Memory Untuk Prediksi Jaminan Kecelakaan Kerja Di Bpjs Ketenagakerjaan Cabang Tanjung Perak Surabaya

Ikhsan, Renaldy Al and Maldini, Andry Syva (2025) Implementasi Deep Learning Dengan Metode Long Short-Term Memory Untuk Prediksi Jaminan Kecelakaan Kerja Di Bpjs Ketenagakerjaan Cabang Tanjung Perak Surabaya. Project Report (Praktek Kerja Lapang). Universitas Pembangunan Nasional Veteran Jawa Timur.

	Text (Cover) 21083010072_Cover.pdf Download (568kB)
	Text (Bab 1) 21083010072_BAB I.pdf Download (133kB)
	Text (Bab 2) 21083010072_BAB II.pdf Restricted to Repository staff only until 25 July 2027. Download (173kB)
	Text (Bab 3) 21083010072_BAB III.pdf Restricted to Repository staff only until 25 July 2027. Download (1MB)
	Text (Bab 4) 21083010072_BAB IV.pdf Restricted to Repository staff only until 25 July 2027. Download (72kB)
	Text (Daftar Pustaka) 21083010072_Daftar Pustaka.pdf Download (69kB)
	Text (Lampiran) 21083010072_Lampiran.pdf Restricted to Repository staff only until 25 July 2027. Download (182kB)

Abstract

Internship at BPJS Employment, as part of the Campus-based Internship Program (MBKM), is organized by the Faculty of Computer Science at the State University of Development "Veteran" East Java and has a duration of one semester (20 credit hours). The aim of this program is to provide practical experience to students, focusing on the concrete aspects of the working world, enabling them to prepare for future professional challenges. Through this internship, students have the opportunity to apply their theoretical knowledge in the operational activities of BPJS Employment, develop a profound understanding of the labor sector, and enhance practical skills. With the increasing number of significant work accident cases in Indonesia, this program reflects the urgency of Occupational Health and Safety (OHS), simultaneously advocating policy reform and raising awareness of workplace risks. The importance of preventive and proactive measures is emphasized to create a safer work environment. Concrete steps include intensifying safety training and conducting in-depth evaluations of existing policies. Data indicates the involvement of all parties, including the government, companies, and workers, is essential to create a safer and healthier work environment. In line with efforts for prevention, hazard identification, and risk assessment in the workplace, the use of deep learning, particularly with the Long Short-Term Memory (LSTM) method, is proposed to predict future trends in work accidents. The success of students in the internship not only provides individual benefits but also fosters a positive relationship between the university and the industry. Presenting the model's prediction results and comparing them with actual total benefits demonstrates pattern similarities, although some differences are observed. Further analysis of these differences can provide additional insights into the model's performance and predictions, serving as a basis for developing more accurate models in the future. Keywords: Occupational Health and Safety (OHS), Deep Learning, Long Short Term Memory (LSTM), Model Development, Work Accident Risks.

Item Type:

Monograph (Project Report (Praktek Kerja Lapang))

Contributors: