Scholarlink

The increasing attention to Big Data Analytics (BDA) in Supply Chain Management (SCM) stems from its versatile applications, encompassing customer behaviour analysis, trend analysis, and demand prediction. This paper aims to explore the potential of predictive BDA applications in supply chain demand forecasting and to pinpoint gaps in existing knowledge. In this proposed work, a time series predictive big data analytics using SARIMA, Prophet and ensemble model is proposed. Further to achieve an improved prediction accuracy, optimal parameters were identified using manual and grid search methods. In addition, geographical feature is extracted using KMeans clustering to understand any underlying patterns. Finally, an ensemble model is proposed that integrates heterogeneous models (SARIMA, Prophet), to achieve improved performance. The experiments were evaluated using five node Spark clusters deployed in the cloud. The results exhibit that the proposed ensemble approach using Linear regression achieves the lowest RMSE of 30.76.

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

An Efficient Predictive Big Data Analytics for Supply Chain Demand Forecasting Through Ensemble Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • S. Navadersh,
  • S. Vengadeswaran

摘要

The increasing attention to Big Data Analytics (BDA) in Supply Chain Management (SCM) stems from its versatile applications, encompassing customer behaviour analysis, trend analysis, and demand prediction. This paper aims to explore the potential of predictive BDA applications in supply chain demand forecasting and to pinpoint gaps in existing knowledge. In this proposed work, a time series predictive big data analytics using SARIMA, Prophet and ensemble model is proposed. Further to achieve an improved prediction accuracy, optimal parameters were identified using manual and grid search methods. In addition, geographical feature is extracted using KMeans clustering to understand any underlying patterns. Finally, an ensemble model is proposed that integrates heterogeneous models (SARIMA, Prophet), to achieve improved performance. The experiments were evaluated using five node Spark clusters deployed in the cloud. The results exhibit that the proposed ensemble approach using Linear regression achieves the lowest RMSE of 30.76.