IMPLEMENTASI MACHINE LEARNING UNTUK PREDIKSI JUMLAH DAN KLASIFIKASI STATUS PERKARA PIDANA UMUM DENGAN METODE LSTM DAN DEEP LEARNING DI KEJAKSAAN NEGERI LABUHANBATU

AHMAD ADRYAN, NPM 2208100005 (2026) IMPLEMENTASI MACHINE LEARNING UNTUK PREDIKSI JUMLAH DAN KLASIFIKASI STATUS PERKARA PIDANA UMUM DENGAN METODE LSTM DAN DEEP LEARNING DI KEJAKSAAN NEGERI LABUHANBATU. Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (4MB)
	Text BAB I.pdf Download (455kB)
	Text BAB II.pdf Download (1MB)
	Text BAB III.pdf Restricted to Registered users only Download (901kB)
	Text BAB IV.pdf Restricted to Registered users only Download (6MB)
	Text BAB V.pdf Download (206kB)
	Text DAFTAR PUSTAKA.pdf Download (201kB)
	Text LAMPIRAN.pdf Download (783kB)

Abstract

Pengelolaan data perkara pidana umum di Kejaksaan Negeri Labuhanbatu melalui Case Management System (CMS) saat ini masih terbatas pada penyajian deskriptif, sehingga belum optimal dalam mendukung perencanaan strategis akibat fluktuasi jumlah perkara. Untuk mengatasi tantangan tersebut, penelitian ini menerapkan pendekatan machine learning dan deep learning yang berfokus pada prediksi jumlah perkara serta klasifikasi status perkara pidana umum. Metode Long Short Term Memory (LSTM) dimanfaatkan untuk menganalisis data deret waktu historis guna memprediksi tren perkara secara akurat. Sementara itu, arsitektur Deep Learning multilapis diterapkan untuk mengklasifikasikan status perkara secara objektif berdasarkan pola kompleks atribut data yang telah melalui tahap pra-pengolahan. Integrasi model LSTM dan Deep Learning ini diharapkan memberikan kontribusi nyata dalam mendorong transformasi digital di lingkungan Kejaksaan Negeri Labuhanbatu. Hasil analisis prediktif dan klasifikasi ini tidak hanya melengkapi aspek akademis dalam ranah komputasi hukum, melainkan juga menyajikan solusi praktis yang adaptif bagi para pengambil kebijakan. Dengan adanya sistem yang responsif terhadap pola data historis, Kejaksaan Negeri Labuhanbatu dapat meningkatkan efisiensi manajemen perkara, ketepatan alokasi sumber daya dan perencanaan kerja, serta memperkuat transparansi dan akuntabilitas dalam tata kelola penegakan hukum. Kata Kunci: Case Management System, Deep Learning, Kejaksaan Negeri Labuhanbatu, Long Short Term Memory (LSTM), Prediksi Perkara =================================================================================================== General criminal case data management at the Labuhanbatu District Attorney's Office through the Case Management System (CMS) is currently limited to descriptive presentation, rendering it suboptimal for supporting strategic planning due to fluctuations in case volume. To address this challenge, this study applies machine learning and deep learning approaches focused on predicting case volumes and classifying general criminal case statuses. The Long Short-Term Memory (LSTM) method is utilized to analyze historical time-series data to accurately forecast case trends. Meanwhile, a multi-layer Deep Learning architecture is applied to objectively classify case statuses based on complex patterns within preprocessed data attributes. The integration of LSTM and Deep Learning models is expected to make a tangible contribution to advancing digital transformation within the Labuhanbatu District Attorney's Office. These predictive and classification analysis results not only contribute to the academic domain of legal computing, but also offer adaptive, practical solutions for decision-makers. With a system responsive to historical data patterns, the Labuhanbatu District Attorney's Office can improve case management efficiency, refine resource allocation and work planning, and strengthen transparency and accountability in law enforcement governance. Keywords: Case Management System, Deep Learning, Labuhanbatu District State Attorney's Office, Long Short-Term Memory (LSTM), Case Forecasting

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Case Management System, Deep Learning, Kejaksaan Negeri Labuhanbatu, Long Short Term Memory (LSTM), Prediksi Perkara===============Case Management System, Deep Learning, Labuhanbatu District State Attorney's Office, Long Short-Term Memory (LSTM), Case Forecasting
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions:	Fakultas Sains Dan Teknologi > Teknologi Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	11 Sep 2026 02:30
Last Modified:	11 Sep 2026 02:30
URI:	http://repository.ulb.ac.id/id/eprint/2802

Actions (login required)

View Item