This Author published in this journals
All Journal OPSI
Nabiha, Gina Almas
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Proposed improvement of product support packaging material defects using the Cross-Industry Standard Process for Data Mining (CRISP-DM) approach Fitriana, Rina; Habyba, Anik Nur; Nabiha, Gina Almas; Mareta, Sannia
OPSI Vol 18 No 1 (2025): OPSI - June 2025
Publisher : Jurusan Teknik Industri, Fakultas Teknologi Industri UPN "Veteran" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/opsi.v18i1.11803

Abstract

This research was conducted because the defect rate of packaging materials supporting lithos M products exceeded the Company's tolerance standard of 2%. This research aims to identify the causes and provide suggestions to improve the Quality of product support packaging materials. The methods used in data mining with the CRISP-DM (Cross-Industry Standard Process For Data Mining) approach. The Business Understanding stage determines the problem and research objectives, Power Business Intelligence, SIPOC (Supplier, Input, Process, Output, Customer) Diagrams, Operation Process Chart, QC Action, and CTQ (Critical to Quality). The Data Understanding stage creates a Control P Chart, calculates DPMO and the sigma level obtained by the unscramble machine dented bottle value 762.31 with a Sigma level of 4.66, Sticker 2nd defect Internal 187.47 with a sigma level of 5.06, Cap 2nd defect internal 67.18 with a sigma level of 5.32, and uses Fault Tree Analysis. The Data Preparation stage performs data cleaning, integration, transformation, and preprocessing. The Modelling stage makes classification with C4.5 and the Cart decision tree algorithm. The evaluation stage uses a Confusion Matrix accuracy of 78.8 percent and 89.4 percent, respectively. The Deployment stage produces improvement proposals by creating a Dashboard, Standard Operating Procedure, and Check Sheet.