Analisis alokasi kredit bank perkreditan rakyat di Indonesia menggunakan machine learning dan shapley additive explanations = Analysis of rural bank credit all ocation in Indonesia using machine learning and shapley additive explanations

Wirjanto, Ferell Aaron (2025) Analisis alokasi kredit bank perkreditan rakyat di Indonesia menggunakan machine learning dan shapley additive explanations = Analysis of rural bank credit all ocation in Indonesia using machine learning and shapley additive explanations. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (267kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (702kB)
[thumbnail of TOC] Text (TOC)
TOC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (693kB)
[thumbnail of Chapter 1] Text (Chapter 1)
Chapter 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (712kB)
[thumbnail of Chapter 2] Text (Chapter 2)
Chapter 2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (995kB)
[thumbnail of Chapter 3] Text (Chapter 3)
Chapter 3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (834kB)
[thumbnail of Chapter 4] Text (Chapter 4)
Chapter 4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter 5] Text (Chapter 5)
Chapter 5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (663kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (706kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)

Abstract

Penelitianini akanfokuspadapemanfaatanberbagai teknikpembelajaranmesin untukmemprediksi alokasi kredit di bank-bank pedesaan danmenggunakan SHapley Additive exPlanations (SHAP) untuk menentukan signifikansi dari berbagai fituryangdigunakandalammodelprediktif. Di Indonesia, kelangkaan fasilitas perbankan tradisional di daerah pedesaan telah mengarah pada pembentukanBankPerkreditanRakyat(BPR),yangbertujuanuntukmenyediakan danmeningkatkan akses kredit bagi komunitas yang kurang terlayani serta mendukungpengembanganekonomidaninklusikeuangan.Studiinimengevaluasi beberapa model pembelajaran mesin, termasuk LightGBM, XGBoost, serta mengeksplorasi efektivitas penggabungan model-model menggunakan regresi lineardalamstackinguntukmengidentifikasipendekatanyangpalingcocokuntuk memprediksi kredit BPRdi Indonesia. Sebelumpemodelan, teknik recursive clusteringditerapkanuntukmemperhitungkankondisiekonomiyangberagamdi seluruhnegeri. NilaiSHAPkemudiandigunakanuntukmenganalisispentingnya fiturdalammodelyangberkinerja terbaikdi setiapklaster. Penemuanstudi ini menunjukkan bahwa model gabungan yangmenggabungkan LightGBM dan XGBoost, dengan Regresi Linear sebagai meta-learner, mencapai akurasi keseluruhan tertinggi dengan hasil terbaiknya memiliki nilai RMSE sebesar 33.1078,MAEsebesar 25.2817danMAPEsebesar 0.9608%. Namun, dalam beberapa kasus, model tunggal dapat melampaui performamodel gabungan. Analisispentingnya fiturmenunjukkanbahwadanapihakketigadanasetBPR adalahprediktoryangpalingberpengaruhkepadakinerjakreditBPR. / This researchfocusesonutilizingmachine learning techniques topredict credit allocation in rural banks and uses SHapleyAdditive exPlanations (SHAP) to determinethesignificanceofvariousmodelfeatures. InIndonesia, thescarcityof traditional bankingfacilities inrural areashas led to theestablishment ofBank Perkreditan Rakyat (BPR), or rural banks, which aim to provide credit to underserved communities and foster economic development and financial inclusion. This study evaluates several machine learningmodels, including LightGBM,XGBoost, andexplores the effectiveness of stacking thesemodels usinglinear regressiontoidentifythemost suitableapproachforpredictingrural bankcredit inIndonesia. Prior tomodeling, clusteringtechniquesareappliedto accountforthediverseeconomicconditionsacrossthecountry. SHAPvaluesare thenusedtoanalyzefeatureimportancewithinthebest-performingmodelofeach cluster. The findings indicate that a stackedmodel combiningLightGBMand XGBoost,withLinearRegressionasthemeta-learner,achievesthehighestoverall accuracywithitsbest resultshavingaRMSEof33.1078,MAEof25.2817and MAPEof0.9608%. However, insomeinstances,standalonemodelsmaysurpass it. Analysisoffeatureimportancerevealsthat third-partyfundsandtheassetsof ruralbanksarecriticalpredictorsofruralbankcreditperformance.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Wirjanto, Ferell Aaron
NIM01112210025
ferellaaron@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Ferdinand, Ferry Vincenttius
NIDN0323059001
ferry.vincenttius@uph.edu
Thesis advisor
Haryani, Calandra Alencia
NIDN0307079302
calandra.haryani@uph.edu
Uncontrolled Keywords: clustering;kredit BPR pembelajaran mesin;SHAP; clustering;machine learning;rural bank credit;SHAP.
Subjects: Q Science > QA Mathematics
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Depositing User: Stefanus Tanjung
Date Deposited: 10 Aug 2025 04:53
Last Modified: 10 Aug 2025 04:53
URI: http://repository.uph.edu/id/eprint/70442

Actions (login required)

View Item
View Item