Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimizing Demand Forecasting Method with Support Vector Regression for Improved Inventory Planning Palgunadi, Tryantomo Lokhilmahful; Fitriana, Rina; Habyba, Anik Nur; Liang, Yun-Chia
Jurnal Optimasi Sistem Industri Vol. 23 No. 2 (2024): Published in January 2025
Publisher : The Industrial Engineering Department of Engineering Faculty at Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1057.205 KB) | DOI: 10.25077/josi.v23.n2.p149-166.2024

Abstract

Problems arising from suboptimal production planning can cause inventory management to be less effective and efficient in the company. The lack of integrated presentation of information also causes less efficiency in making decisions. This study aims to obtain the best kernel function forecasting model by predicting ground rod sales using the Support Vector Regression (SVR) method in order to determine the level of forecasting accuracy and the results of ground rod forecasting in the future which are presented in an optimal data visualization. This problem-solving is done with the Support Vector Regression method, which consists of linear kernel functions, polynomial kernel functions, and radial basis function (RBF) kernel functions with the Grid Search Algorithm. Based on the results of the best parameter search that has been done using the grid search algorithm, it can be concluded that the best kernel function forecasting model is a linear kernel function with a value of C = 100 and ε = 10-3. The accuracy of this forecasting model has a MAPE value of training data and testing data of 2.048% and 1.569%, where this value is the smallest MAPE value compared to the MAPE value of the other two functions. After getting the best model, forecasting was carried out within five months, obtaining an average of 6,647 monthly pieces. The results of forecasting and historical sales are reviewed in a visualization of Business Intelligence data so that it is well exposed, where the forecasting shows an increase from every month.
Enhancing Quality Control of Packaging Product: A Six Sigma and Data Mining Approach Ramadhani, Resty Ayu; Fitriana, Rina; Habyba, Anik Nur; Liang, Yun-Chia
Jurnal Optimasi Sistem Industri Vol. 22 No. 2 (2023): Published in December 2023
Publisher : The Industrial Engineering Department of Engineering Faculty at Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (807.476 KB) | DOI: 10.25077/josi.v22.n2.p197-214.2023

Abstract

Six Sigma is of paramount importance to organizations as it provides a structured and data-driven approach, fostering continuous improvement, minimizing defects, and optimizing processes to meet and exceed customer expectations. In response to the increasing defects of packaging product in a cosmetics industry in Indonesia, surpassing the specified 3% tolerance limit, this research conducts a thorough investigation into the root causes, corrective measures, and improvement proposals to elevate product quality. By leveraging the Six Sigma method and data mining techniques, the study systematically addresses the complexities associated with defect reduction in packaging for cosmetics product. The research methodology encompasses defining the problem through SIPOC and Critical to Quality (CTQ) diagrams, measuring via control charts and sigma level calculations, and analyzing using tools like pareto diagrams, Apriori algorithms, fishbone diagrams, and Fault Mode and Effect Analysis (FMEA). Key findings reveal a notable correlation between spot defects and varying colors, leading to pearl defects as identified by the Apriori algorithm. FMEA identifies critical failures, including suboptimal printing plate conditions, clumpy ink usage, and insufficient operator attention to ink filling. The improvement stage proposes practical solutions, such as implementing alarms and buzzers, color-indicator-adjusted ink storage labels, and a structured form for cleaning and monitoring printing plates. These findings carry significant implications, providing a tailored roadmap for enhancing the quality of cosmetic packaging. The anticipated implementation of proposed improvements aims to elevate customer satisfaction by addressing specific pain points in the production process. Furthermore, the research contributes valuable insights to the broader cosmetics industry, offering effective methodologies for defect reduction and quality enhancement in packaging processes.