Usfaliana, Desi (2019) Pemodelan Frekuensi Pembayaran Kredit Usaha Rakyat (KUR) Yang Gagal Bayar Dari Tiga Bank Pelaksana Di PT. Askrindo (Persero) Cabang Surabaya Menggunakan Bayesian Geometric Regression Dan Bayesian Mixture Geometric Regression. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211745000008-Undergraduate_Theses.pdf Download (3MB) | Preview |
Abstract
Kredit Usaha Rakyat (KUR) adalah salah satu upaya pemerintah da-lam meningkatkan kualitas dan kuantitas UMKM di Indonesia dengan cara memberikan akses pembiayaan modal usaha dengan pola penjaminan. Namun dalam realisasi penyaluran KUR terdapat kendala yaitu permasalahan nasabah gagal bayar (risiko default) sehingga menyebabkan pengajuan penjaminan kepada PT. Askrindo Cabang Surabaya selaku perusahaan penjamin KUR untuk 8 wilayah di Jawa Timur oleh pihak Bank. Risiko dari permasalahan nasabah KUR yang gagal bayar adalah menurunnya profitabilitas bagi pihak Bank maupun perusahaan penjamin. Sehingga untuk meminimalisir terjadinya risiko tersebut, maka dilakukan pemodelan faktor-faktor yang diduga mempengaruhi ketahanan nasabah dalam membayar angsuran KUR ditinjau dari frekuensi pembayaran KUR hingga dinyatakan gagal bayar dimana frekuensi tersebut berdistribusi geometri. Pemodelan dilakukan dengan Bayesian Geometric Regression dan Bayesian Mixture Geometric Regression. Pemodelan dengan Bayesian Geometric Regression lebih baik dalam memodelkan frekuensi pembayaran KUR karena memiliki nilai DIC lebih kecil dibandingkan dengan Bayesian Mixture Geometric Regression. Berdasarkan pemodelan dengan Bayesian Geometric Regression diperoleh variabel yang signifikan adalah sektor usaha, wilayah usaha, jumlah pinjaman, dan suku bunga.
==============================================================================================================================
Kredit Usaha Rakyat (KUR) is one of the government's efforts to improve the quality and quantity of UMKMs in Indonesia by providing access to business capital financing with a guarantee. However, in the realization of KUR distribution there was problem, it is the failure of customers to make credit payment (default risk), which cause claims to PT. Askrindo Surabaya as KUR’s guarantor company for 8 regions in East Java by the Bank. The risk of KUR’s customer defaults is decreasing profitability for the Bank and the guarantor company. Therefore, to minimize the default risk is determine the factors that affect survival of customers to make KUR payment, in terms of frequency of KUR payments by customers that are distributed geometry. The modelling using Bayesian Geometric Regression and Bayesian Mixture Geometric Regression. The best model of this research is modelling using Bayesian Geometric Regression method because has lower DIC values than Bayesian Mixture Geometric Regression. Model-ling using Bayesian Geometric Regression show the significant variables are business sector, region of business, amount of loan, and interest rate.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.542 Usf p-1 2019 |
| Uncontrolled Keywords: | Bayesian, Kredit Bermasalah, Kredit Usaha Rakyat, Geometric Regression, Mixture Geometric Regression |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation H Social Sciences > HA Statistics > HA31.7 Estimation Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory. |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Desi Usfaliana |
| Date Deposited: | 10 Jan 2023 03:17 |
| Last Modified: | 10 Jan 2023 03:17 |
| URI: | http://repository.its.ac.id/id/eprint/63568 |
Actions (login required)
 |
View Item |