{
      "department": "FAKULTAS SAINS DAN TEKNOLOGI",
      "subjects": [
        515.6
      ],
      "eprintid": 78704,
      "thesis_type": "skripsi",
      "date": "2026-08-12",
      "userid": 12460,
      "documents": [
          {
            "language": "id",
            "placement": 1,
            "eprintid": 78704,
            "files": [
                {
                  "hash_type": "MD5",
                  "mtime": "2026-10-06 03:30:53",
                  "datasetid": "document",
                  "fileid": 1874580,
                  "objectid": 1078972,
                  "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/file\/1874580",
                  "mime_type": "application\/pdf",
                  "hash": "bc1be86cdf066f5c58bff96f9d22da21",
                  "filesize": 5835847,
                  "filename": "22106010087_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf"
                }
            ],
            "content": "published",
            "rev_number": 3,
            "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/document\/1078972",
            "main": "22106010087_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf",
            "mime_type": "application\/pdf",
            "docid": 1078972,
            "format": "text",
            "security": "public",
            "pos": 1,
            "formatdesc": "PEMILIHAN MODEL REGRESI LOGISTIK LASSO MENGGUNAKAN AIC: STUDI KASUS PREDIKSI DEFAULT KREDIT"
          },
          {
            "language": "id",
            "placement": 2,
            "eprintid": 78704,
            "files": [
                {
                  "hash_type": "MD5",
                  "mtime": "2026-10-06 03:30:55",
                  "datasetid": "document",
                  "fileid": 1874583,
                  "objectid": 1078973,
                  "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/file\/1874583",
                  "mime_type": "application\/pdf",
                  "hash": "2658ccceba46c9bf8b878bcfc3559076",
                  "filesize": 5915035,
                  "filename": "22106010087_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf"
                }
            ],
            "content": "published",
            "rev_number": 3,
            "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/document\/1078973",
            "main": "22106010087_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf",
            "mime_type": "application\/pdf",
            "docid": 1078973,
            "format": "text",
            "security": "validuser",
            "pos": 2,
            "formatdesc": "PEMILIHAN MODEL REGRESI LOGISTIK LASSO MENGGUNAKAN AIC: STUDI KASUS PREDIKSI DEFAULT KREDIT"
          }
      ],
      "rev_number": 10,
      "creators": [
        {
          "name": {
            "lineage": null,
            "given": "NIM.: 22106010087",
            "honourific": null,
            "family": "Lucky Ramadhani"
          }
        }
      ],
      "dir": "disk0\/00\/07\/87\/04",
      "keywords": "Credit Scoring, Regresi Logistik, LASSO, AIC, Risiko Gagal Bayar",
      "lastmod": "2026-10-06 03:34:57",
      "ispublished": "pub",
      "metadata_visibility": "show",
      "date_type": "published",
      "eprint_status": "archive",
      "status_changed": "2026-10-06 03:34:57",
      "datestamp": "2026-10-06 03:34:57",
      "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/eprint\/78704",
      "thesis_name": "other",
      "note": "Sri Utami Zuliana, S.Si., M.Sc., Ph.D.",
      "full_text_status": "restricted",
      "contact_email": "muh.khabib@uin-suka.ac.id",
      "divisions": [
        "jur_mat"
      ],
      "abstract": "Credit default risk poses a major challenge in the banking industry, which can\r\nbe mitigated through predictive credit scoring models. This study predicts credit card\r\ndefault risk using Least Absolute Shrinkage and Selection Operator (LASSO) logistic\r\nregression optimized by the Akaike Information Criterion (AIC). The LASSO method\r\neliminates redundant and highly correlated transaction variables (multicollinearity),\r\nwhile AIC selects the simplest and most accurate model architecture. Utilizing 30,000\r\ncustomer records from the UCI Machine Learning Repository partitioned into 80%\r\ntraining and 20% testing sets, the algorithm successfully removed two redundant\r\nbilling variables (BILL AMT4 and BILL AMT5) at the optimal penalty level of λ =\r\n0.0002013. The final model achieved an overall accuracy of 81.16%, a specificity of\r\n97.20% in identifying non-default customers, and an AUC discrimination power of\r\n0.7202. Furthermore, risk factor analysis revealed that the most recent repayment delay\r\n(PAY 1) is the most critical trigger, multiplying default risk by 1.766 times per delay\r\nlevel. This study concludes that integrating LASSO with AIC yields a concise, stable,\r\nand practical credit scoring system to assist banks in detecting high-risk borrowers\r\nearly.",
      "type": "thesis",
      "title": "PEMILIHAN MODEL REGRESI LOGISTIK LASSO MENGGUNAKAN AIC: STUDI KASUS PREDIKSI DEFAULT KREDIT",
      "institution": "UIN SUNAN KALIJAGA YOGYAKARTA",
      "pages": 67
    }