Perbaikan kualitas produk pre-print box nh1x36b dengan pendekatan qm – crisp dm PT Satyamitra Kemas Lestari
P PT Satyamitra Kemas Lestari merupakan produsen packaging box yang produknyadiperlukan berbagai industri. Permasalahan pada Pre-Print Box NH1X36B, yangmerupakan kardus sepatu, adalah tingginya tingkat kecacatan, yakni sebesar2,345%. Dengan defect allowance sebesar 2%, diperlukan upaya perbaikan untukmeningkatkan kualitas. Penelitian ini bertujuan untuk mengurangi tingkatkecacatan produk Pre-print Box NH1X36B. Pendekatan Quality-Management(QM) dan Cross Industry Standard Process for Data Mining (CRISP-DM)dilakukan dengan pengintegrasian Six Sigma dan data mining menggunakanframework CRISP-DM. Pada Business Understanding dilakukan pendefinisianobjektif bisnis dan data mining, pembuatan diagram SIPOC (Supplier-InputProcess-Output-Customer), dan penentuan Critical-to-Quality (CTQ). Pada DataUnderstanding, diketahui nilai Defects Per Million Opportunities (DPMO) sebesar1210,12. Tahap Data Preparation dilakukan data cleaning, reduction, dantransformation. Berdasarkan hasil Modeling dengan Decision Tree C4.5 dan FPGrowth, diketahui atribut dominan penyebab reject tinggi adalah belobor, hickies,varnish tidak rata, dan delaminasi. Akurasi model sebesar 90.24% menandakanmodel berperformansi baik. Analisis menggunakan FMEA menghasilkan prioritasperbaikan pada kecacatan belobor, varnish tidak rata, dan delaminasi. Implementasiusulan perbaikan pada tahap Deployment adalah pengaplikasian form pembersihandan pemasangan plat, checklist proses printing, serta SOP inspeksi sheet. Hasilimplementasi menunjukkan keberhasilan upaya perbaikan kualitas denganpeningkatan sigma dari 4,533 menjadi 4,648 sigma dan penurunan tingkatkecacatan menjadi 1,559%.
P PT Satyamitra Kemas Lestari is a manufacturer of packaging box whose productsare indispensable for various fields. The problem identified in NH1X36B PrePrinted Box, which is a shoes box, is the high defect rate of 2,345% that exceedcompany target of 2%. This study aims to reduce the defect rate of the product. TheQuality-Management (QM) and Cross Industry Standard Process for Data Mining(CRISP-DM) approach was conducted by integrating Six Sigma and data mining.The Business Understanding phase was intended to define business and data miningobjectives, SIPOC (Supplier-Input-Process-Output-Customer) diagram, andCritical-to-Quality (CTQ). In Data Understanding phase, it was known that theDefects Per Million Opportunities (DPMO) value was 1210,12. Data preparationphase was carried out with data cleaning, reduction, and transformation. Based onthe Modeling result using Decision Tree C4.5 and FP-Growth algorithm, it wasknown that the dominant attributes causing high rejection were overflow ink, whitespots, uneven varnish, and delamination. Accuracy of the model is 90.24%indicating that the model is performing well. Analysis using FMEA yielded prioritycorrection to the causes of overflow ink, uneven varnish, and delamination. Processimprovement in Deployment phase was the application of plate cleaning andinstallation form, printing process check sheet, and SOP for sheets inspection. Theimprovement plans managed to improve the quality by rising sigma level from4,533 to 4,648 sigma and reduce defect rate to 1,559%.