CREDIT SCORING DAN DETEKSI PADA DUGAAN TINDAK PENCUCIAN UANG DENGAN ALGORITMA NAIVE BAYES

RAHMAWAN, TUBAGUS LINGGA (2023) CREDIT SCORING DAN DETEKSI PADA DUGAAN TINDAK PENCUCIAN UANG DENGAN ALGORITMA NAIVE BAYES. S1 thesis, Universitas Mercu Buana.

	Text (COVER) 01 Cover.pdf Download (390kB)
	Text (ABSTRAK) 02 Abstrak.pdf Download (33kB)
	Text (BAB I) 03 Bab 1.pdf Restricted to Registered users only Download (142kB)
	Text (BAB II) 04 Bab 2.pdf Restricted to Registered users only Download (176kB)
	Text (BAB III) 05 Bab 3.pdf Restricted to Registered users only Download (57kB)
	Text (BAB IV) 06 Bab 4.pdf Restricted to Registered users only Download (610kB)
	Text (BAB V) 07 Bab 5.pdf Restricted to Registered users only Download (36kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (137kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (1MB)

Abstract

This research aims to develop a credit scoring and money laundering detection model using the Naive Bayes algorithm optimized with Particle Swarm Optimization (PSO). The study focuses on the Statlog German Credit dataset to analyze credit-related variables and detect potential money laundering patterns. The sample size consists of N samples, obtained through purposive sampling. The data analysis method involves applying the Naive Bayes algorithm and optimizing the model using PSO. The optimized Naive Bayes model demonstrates significant improvements in accuracy and AUC-ROC compared to the initial model. For credit scoring, the optimized model achieved an accuracy of 80.67% and an AUC-ROC of 0.803, surpassing the initial model's accuracy of 69.67% and AUC-ROC of 0.647. Similarly, for money laundering detection, the optimized model achieved an accuracy of 98.67% and an AUC-ROC of 0.999, outperforming the initial model's accuracy of 97.67% and AUC-ROC of 0.990. The research highlights the potential of optimization techniques in enhancing the performance of predictive models for credit scoring and money laundering detection. The findings contribute to improving credit risk assessment and preventing money laundering activities in the financial industry. The study suggests practical applications for utilizing the optimized Naive Bayes model with PSO to enhance decision-making processes and mitigate financial risks. Keywords: Credit scoring, Money laundering detection, Naive Bayes algorithm, Particle Swarm Optimization (PSO), Statlog German Credit dataset Penelitian ini bertujuan untuk mengembangkan model deteksi credit scoring dan money laundering menggunakan algoritma Naive Bayes yang dioptimasi dengan Particle Swarm Optimization (PSO). Studi ini berfokus pada kumpulan data Statlog German Credit untuk menganalisis variabel terkait kredit dan mendeteksi potensi pola pencucian uang. Besar sampel terdiri dari N sampel yang diperoleh melalui purposive sampling. Metode analisis data melibatkan penerapan algoritma Naive Bayes dan pengoptimalan model menggunakan PSO. Model Naive Bayes yang dioptimalkan menunjukkan peningkatan signifikan dalam akurasi dan AUCROC dibandingkan dengan model awal. Untuk penilaian kredit, model yang dioptimalkan mencapai akurasi 80,67% dan AUC-ROC 0,803, melampaui akurasi model awal 69,67% dan AUC-ROC 0,647. Demikian pula, untuk deteksi pencucian uang, model yang dioptimalkan mencapai akurasi 98,67% dan AUC-ROC 0,999, mengungguli akurasi model awal 97,67% dan AUC-ROC 0,990. Penelitian ini menyoroti potensi teknik pengoptimalan dalam meningkatkan kinerja model prediktif untuk penskoran kredit dan deteksi pencucian uang. Temuan ini berkontribusi untuk meningkatkan penilaian risiko kredit dan mencegah kegiatan pencucian uang di industri keuangan. Studi ini menyarankan aplikasi praktis untuk memanfaatkan model Naive Bayes yang dioptimalkan dengan PSO untuk meningkatkan proses pengambilan keputusan dan memitigasi risiko keuangan. Kata Kunci : Penilaian kredit, Deteksi pencucian uang, Algoritma Naive Bayes, Particle Swarm Optimization (PSO), dataset Statlog German Credit

Actions (login required)

View Item