Scholarlink

In the vastly changing environment of smart manufacturing, the accuracy of the sales forecast is highly important for the optimization of inventory management and strategic planning. This research keeps in sight the high need for robust prediction models that can further improve real-time decisions in sales forecasting. From this perspective, Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) machine learning techniques have been applied to predict mobile phone sales from a multifarious dataset that includes historical sales, pricing, marketing campaigns, and seasonal factors. This research also used the Ant colony optimization (ACO) algorithm to tune hyperparameters to improve prediction accuracy. The results showed that the ANN model outperformed the others in classifying correctness with an accuracy of 98.76%, having low loss in data compared to the SVM, DT, and RF. This superior performance indicates ANN’s higher capability of capturing complex patterns and interactions in the sales data. This research breaks that by pointing out the application of ANN to real-time sales forecasting systems, which is an advantageous tool for businesses to improve inventory control, optimize marketing strategies, and improve overall operational efficiency. Companies might be able to achieve even more precise demand predictions, improving resource allocation and strategic planning, by incorporating ANN into smart manufacturing environments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Applying Machine Learning and Swarm Optimization Techniques for Real-Time Decision-Making in Supply Chain Management

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anshul Sharma,
  • Jagendra Singh,
  • Preeti Sharma,
  • Vinish Kumar,
  • Meenakshi Sharma,
  • Ramendra Singh

摘要

In the vastly changing environment of smart manufacturing, the accuracy of the sales forecast is highly important for the optimization of inventory management and strategic planning. This research keeps in sight the high need for robust prediction models that can further improve real-time decisions in sales forecasting. From this perspective, Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) machine learning techniques have been applied to predict mobile phone sales from a multifarious dataset that includes historical sales, pricing, marketing campaigns, and seasonal factors. This research also used the Ant colony optimization (ACO) algorithm to tune hyperparameters to improve prediction accuracy. The results showed that the ANN model outperformed the others in classifying correctness with an accuracy of 98.76%, having low loss in data compared to the SVM, DT, and RF. This superior performance indicates ANN’s higher capability of capturing complex patterns and interactions in the sales data. This research breaks that by pointing out the application of ANN to real-time sales forecasting systems, which is an advantageous tool for businesses to improve inventory control, optimize marketing strategies, and improve overall operational efficiency. Companies might be able to achieve even more precise demand predictions, improving resource allocation and strategic planning, by incorporating ANN into smart manufacturing environments.