Authors : Khandakar Rabbi Ahmed, Arafat Hossain, MD Amaddus Bepary Asif, Mahathir Mohammad, Mustafizur Rahaman, MD Arafat Dewan
Publication date : 2025/2/27
Conference : 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC)
Pages : 86-91
Publisher : IEEE
Description : Manufacturing defective items is one of the challenges for production efficiency and inventory control. Conventional approaches like Economic Order Quantity (EOQ) and Just-in-Time (JIT) often fall short of the flexibility needed to respond to quality variations in real time. It promotes defect detection and control by employing machine learning (ML) for inventory management. Four classifiers were tested using the UCI SECOM dataset (Bagging, AdaBoost, Gradient Boosting, and Random Forest) to identify defective items. We used effective preprocessing techniques to boost model performance, such as SMOTE for class balancing and PCA for reducing dimensionality and standardization. The bagging and random forest classifiers produced 96.6% and 96.9% test accuracies, with good precision and recall scores. Within this context, we propose an Adaptive Inventory Management Framework comprising machine …
Total citations : Cited by 23
Scholar articles :
KR Ahmed, A Hossain, MDAB Asif, M Mohammad… – 2025 3rd International Conference on Intelligent …, 2025