Scholarlink

<p>Demand forecasting has been recognized as a crucial factor in influencing the inventory levels and ordering decisions in manufacturing supply chain systems. This paper aims to propose a straightforward and univariate demand forecasting process based on the autoregressive integrated moving average model and its application in a monthly demand forecasting problem for manufacturing items, particularly nuts, bolts, and screws. The proposed procedure for demand forecasting aligns well with the Box–Jenkins modeling approach and involves steps for data visualization, stationarity testing through the Augmented Dickey–Fuller test, variance stabilization and detrending of the time series, and finally, residual analysis for assessing the performance of the proposed model. The performance of the proposed model in demand forecasting is assessed through appropriate metrics for measuring the errors.</p>

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

Study of demand forecasting using time-series analysis (ARIMA): a manufacturing supply-chain case study

  • 期刊论文

  • 发表日期：

    2026年6月26日

查看全文
  • Vivek Kumar Pathak,
  • Salim,
  • Tanmay Tiwari,
  • Marmik Chaurasia,
  • Gyanendra Bagri

摘要

Demand forecasting has been recognized as a crucial factor in influencing the inventory levels and ordering decisions in manufacturing supply chain systems. This paper aims to propose a straightforward and univariate demand forecasting process based on the autoregressive integrated moving average model and its application in a monthly demand forecasting problem for manufacturing items, particularly nuts, bolts, and screws. The proposed procedure for demand forecasting aligns well with the Box–Jenkins modeling approach and involves steps for data visualization, stationarity testing through the Augmented Dickey–Fuller test, variance stabilization and detrending of the time series, and finally, residual analysis for assessing the performance of the proposed model. The performance of the proposed model in demand forecasting is assessed through appropriate metrics for measuring the errors.