View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Pemodelan Permintaan Market Kredit Online

      Thumbnail
      View/Open
      Cover (1.969Mb)
      Fulltext (12.39Mb)
      Lampiran (337.2Kb)
      Date
      2023
      Author
      Daud, Ibnu
      Suharjo, Budi
      Sumarno, Hadi
      Metadata
      Show full item record
      Abstract
      Penelitian menggunakan data demography dari perusahaan kreditur online. Masalahnya adalah menemukan kriteria market yang tepat, sehingga diperlukan analisis untuk memprediksi variabel yang memengaruhi status calon kreditur menerima pinjaman. Metode yang digunakan adalah supervised learning: random forest classifier, k-NN models, dan logistic linear regression. Dari exploratory data didapatkan bahwa 50,1% adalah kreditur yang berhasil mendapatakn pinjaman dan sisanya adalah Non-ACC Credit sebesar 49,9%. 59,9% calon kreditur berlatar pendidikan sekolah menengah, 20,1% lulusan S1, 14% mereka yang menempuh jenjang diploma, 3,8% adalah pasca-sarjana, dan sisanya 2,1% lulusan sekolah dasar. Status pernikahan didapat 49,1% adalah calon kreditur belum menikah, 48,8% sudah menikah, 1,2% sudah/sedang bercerai, dan sisanya 0,8% adalah janda/duda karena kematian. Untuk membandingkan model menggunakan Confusion Matrix dan didapat bahwa random forest classifier mempunyai nilai persentase terbaik dari semua parameter accuracy, sensitivity, precision, dan F1 score masing-masing adalah 51%. Sedangkan k-NN dan logistic linear regression masing-masing seebesar 50% untuk setiap parameter tersebut.
       
      The research uses demographic data from online creditor companies. The problem is finding market criteria, so analysis is needed to predict the variables that affect the status of prospective creditors receiving loans. The methods are Random Forest Classifier, k-NN Models, and Logistic Linear Regression. Exploratory data shows that 50,1% are creditors who have successfully obtained loans and 49,9% are Non- ACC Credit. 59,9% of prospective creditors have a high school education background, 20.1% have a bachelor, 14% have a diploma, 3,8% postgraduate, and 2,1% have elementary school. Marital status obtained 49,1% single, 48,8% married, 1,2% divorced/divorced, and the remaining 0,8% widow/widower due to death. To compare the models using the Confusion Matrix and it was found that the Random Forest Classifier has the best percentage value of all parameters Accuracy, Sensitivity, Precision, and F1 Score each is 51%. Meanwhile, k-NN and Logistic Linear Regression are 50% each for each of these parameters.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/123301
      Collections
      • UT - Mathematics [1487]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository