• Sumit Kumar Agrawal
• Er. Priyanshi

In the contemporary landscape of supply chain management, ensuring inventory quality while controlling costs is paramount. This study explores the application of machine learning techniques to predict inventory defects and thereby reduce associated expenses. By harnessing a diverse dataset obtained from manufacturing and distribution environments, we developed and evaluated several predictive models, including ensemble methods and deep neural networks, to identify underlying patterns that signal potential defects. The methodology emphasizes rigorous feature selection and data preprocessing to enhance model accuracy and interpretability. Results indicate that the predictive models can successfully forecast defect occurrences with high reliability, enabling proactive measures that substantially lower waste and operational costs. The integration of these models into inventory management systems not only streamlines quality control processes but also contributes to improved resource allocation and overall operational efficiency. This research underscores the transformative role of machine learning in modern inventory systems, providing a strategic pathway for organizations aiming to enhance product quality and achieve cost reductions. Future research directions include real-time model deployment and continuous learning mechanisms to adapt to evolving production conditions, thereby further bolstering the robustness and economic impact of the proposed approach.

Machine Learning, Inventory Defect Prediction, Cost Reduction, Predictive Analytics, Quality Control, Supply Chain Management, Data Preprocessing, Ensemble Methods, Deep Neural Networks, Operational Efficiency.

"Leveraging Machine Learning for Inventory Defect Prediction and Cost Reduction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.h620-h640, March-2025, Available :http://www.jetir.org/papers/JETIR2502778.pdf

"Leveraging Machine Learning for Inventory Defect Prediction and Cost Reduction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. pph620-h640, March-2025, Available at : http://www.jetir.org/papers/JETIR2502778.pdf