Employing a Machine Learning-Based Approach for Enhanced Big Data Analysis in Supply Chain Management

This study uses machine learning models as potent analytical tools to look into the issue of inventory cost and profit prediction in the automobile industry. Throughout a ten-year dataset from 2012 to 2023, the study carefully analyses several cost components and profit data, illuminating the complex relationships between these elements. To provide insights into inventory dynamics, the Convolutional Neural Network (CNN), k-nearest Neighbours (KNN), and Support Vector Machine (SVM) models are rigorously trained and tested. An impressive feat is achieved by the CNN model, which achieves a phenomenal accuracy of 98.7
^%
, followed by KNN at 96.7
^%
and SVM at 93.4%. Additional proof of the models' propensity to make accurate predictions comes from their precision, recall, F1 score, and confusion matrices. The research provides data-driven insights that players in the dynamic vehicle industry can use to improve inventory management procedures and financial results. This work serves as an example of how machine learning may fundamentally alter how people make decisions in this difficult domain.