Ditemukan 125670 dokumen yang sesuai dengan query
Wike Ulfiani Aresa
"Saat ini credit scoring calon nasabah produk Kreasi Pegadaian masih menggunakan scorecard konvensional berupa pembobotan pertanyaan. Model credit scoring tersebut dibangun berdasarkan pengalaman pakar (expert scorecard) dan kemungkinan ada unsur subjektivitas dalam penilaian kelayakan kredit. Untuk mengatasi masalah tersebut, penelitian ini membangun model credit scoring dengan pendekatan data mining menggunakan data riwayat kredit nasabah produk Kreasi (data driven scoring) menggunakan algoritma klasifikasi, diantaranya: support vector machine (SVM), naïve bayes, decision tree dan neural network. Pengembangan model dilakukan dengan menggunakan metodologi CRISP-DM (The Cross Industry Standard Process for Data Mining). Model dibangun dengan kriteria tanpa penggunaan feature selection dan dengan feature selection. Teknik SMOTE (Synthetic Minority Over Sampling Technique) dan Oversampling dipilih untuk menyeimbangkan class data. Dari hasil evaluasi kinerja model menunjukan model SVM dengan feature selection dan penyeimbangan class menggunakan teknik Oversampling dipilih sebagai model dengan kinerja terbaik.
Currently, the credit worthiness of Pegadaian prospective customers still uses a conventional scorecard in the form of weighting questions. The model is built based on expert experience which is called expert scorecard. There might be an element of subjectivity in credit assessment. To resolve that problem, in this research data mining classification techniques are used to build credit scoring models. There are four classification algorithms, namely SVM (Support Vector Machine), Naïve Bayes, Decision Tree and Neural Network as a classification algorithm. Modelling uses the historical customer credit data of Pegadaian Kreasi product. CRISP-DM (The Cross Industry Standard Process for Data Mining) is used as a development methodology. Modeling is done with two criteria, by considering the use of feature selection and without feature selection. The SMOTE (Synthetic Minority Over Sampling Technique) and Oversampling techniques are chosen to balance the class data. The result of this research shows the SVM model with feature selection and data balancing using the Oversampling technique was chosen as the model with the best performance."
Depok: Fakultas Ilmu Komputer Universitas Indonesia, 2020
TA-pdf
UI - Tugas Akhir Universitas Indonesia Library
Adityan Iguh Sasmito
"Pensiun adalah jaminan hari tua dan penghargaan atas jasa aparatur sipil negara yang telah mengabdikan diri kepada negara. PT Taspen (Persero) sebagai Badan Usaha Milik Negara yang diberikan tugas oleh pemerintah untuk mengelola asuransi sosial aparatur sipil negara memiliki tantangan untuk memastikan uang pensiun disalurkan secara tepat. Pada pembayaran pensiun untuk kelompok janda/duda masih ditemukan ketidaktepatan pembayaran karena status pensiun janda/duda yang tidak teridentifikasi seperti telah menikah kembali.
Penelitian ini bertujuan membentuk model prediksi status pensiun janda/duda yang memiliki potensi menikah kembali. Proses prediksi status pensiun janda/duda menggunakan teknik data mining klasifikasi dengan menggunakan data demografi, sosial ekonomi peserta pensiun dan data transaksi proses pengambilan pensiun pada kelompok pensiun janda/duda. Sebagai perbandingan digunakan 3 algoritma klasifikasi yaitu Decision Tree, Naïve Bayes dan Support Vector Machine.
Beberapa atribut yang berpengaruh dalam penelitian ini yaitu jenis kelamin, usia, usia pernikahan sebelumnya, usia status janda/duda, dan kode pengambilan pensiun selama 3 bulan terakhir. Model yang terbentuk memberi wawasan bahwa pensiun duda dan semakin muda usia pernikahan, usia peserta serta usia status janda/duda memiliki potensi yang tinggi untuk menikah kembali. Hasil penelitian menunjukkan algoritma Support Vector Machine memiliki kinerja yang paling baik dengan tingkat akurasi sebesar 89,23%.
Pension is a guarantee of old age and appreciation for the services of state civil servants who have devoted themselves to the state. PT Taspen (Persero) as a state-owned company given the task of managing the social insurance of the state civil servants has a challenge to ensure pension money is distributed appropriately. The pension payments for the widows/widowers were still found to be overdue because the pension for widows/widowers who had remarried was not identified. This study aims to predict changes in the pension status of widows/widowers who have the potential to remarry. This study aims to form a prediction model for the pension status of widows/widowers who have the potential to remarry. The process of predicting the pension status of widows/widowers uses classification data mining techniques using demographic, socio-economic data of pension participants and data on pension retrieval processes in the widow/widower pension group. As a comparison, 3 classification algorithms are used, Decision Tree, Naïve Bayes and Support Vector Machine. Some of the influential attributes in this study are gender, age, age of previous marriage, age of widow/widower status, and retirement retirement code for the last 3 months. The model that is formed provides an insight that the retirement of the widower and/or the younger the age of marriage, the age of the participants and the age of the widow/widower status have a high potential for remarriage. The results showed that the Support Vector Machine algorithm has the best performance with an accuracy rate of 89.23%."
Depok: Fakultas Ilmu Kompter Universitas Indonesia, 2021
TA-pdf
UI - Tugas Akhir Universitas Indonesia Library
Naufal Allaam Aji
"
Non-performing loans has been one of the biggest problems in the banking sector. One alternative to minimize credit risk is to improve the evaluation of the applicant's credibility. Credit risk assessment methods must be improved. Credit scoring is an evaluation of the feasibility of credit requests. Poor credit can lead to an increase in non-preforming loans that may reduce bank productivity even in the event of financial crises and financial institutions bankruptcy. The number of Data-mining-based Credit scoring model has increased. The performance of classifiers in solving financial problem become the main reason why it is growing rapidly. Previously, credit scoring is based on the conventional statistics such as logistic regression and discriminant analysis. Eventhough those techniques produce a good accuracy, some of the assumptions cannot be accomplished by the data. Along the development of infromation technology, more advance approach named data mining has been developed. Therefore, this study performs Data Mining approach to solve NPL percentage problems in Bank. The classification methods that will be used is Decision Tree C4.5, Back Propagation Neural Network, and ensemble classifier algorithms. Classifier with the best accuracy is Decision Tree C4.5 with Adaboost with 98,87% The best sensitivity also performed by Decision Tree C.5 complemented by adaboost with 97,3%. It is considered as the best model in terms of prevent the type II error which could impact to the increase of non-performing loan in a bank.
"
Depok: Fakultas Teknik Universitas Indonesia, 2019
S-pdf
UI - Skripsi Membership Universitas Indonesia Library
Valida Herianty
"Seiring dengan berkembangnya industri kredit, resiko kredit telah menjadi hal yang penting bagi instansi keuangan. Sehingga, penggunaan metode yang tepat dalam menilai resiko dari setiap permohonan kredit perlu dilakukan. Credit scoring merupakan salah satu metode penilaian resiko kredit yang sering digunakan dan sudah banyak dibuat dengan menggunakan berbagai metode data mining. Penelitian ini akan mengaplikasikan metode CART dalam membuat model credit scoring dengan menggunakan kasus di Koperasi. Model credit scoring hasil penelitian ini memiliki tingkat akurasi yang cukup tinggi (83,62%) dan Type I Error yang rendah (4,04%). Namun, model ini memiliki Type II Error yang cukup tinggi yaitu, 53,23%.
With the rapid growth of credit industry, credit risk has become critical for financial institutions. Thus, using the best methods of assessing risk for credit applicants are needed. Credit scoring is one of the method of credit risk measurement, and has been widely developed by using various data mining techniques. This study will implement CART for constructing credit scoring model using data of microfinance institution. As the results, the credit scoring model has high accuracy (83,62%) and low Type I Error (4,04%). While its Type II Error is high (53,23%)."
Depok: Fakultas Teknik Universitas Indonesia, 2015
S60194
UI - Skripsi Membership Universitas Indonesia Library