A hybrid forecasting model with logistic regression and neural networks for improving key performance indicators in supply chains

Abstract

This study investigates the potential of predictive analytics in improving Key Performance Indicators (KPIs) forecasting by leveraging Lean implementation data in supply chain enterprises. A novel methodology is proposed, incorporating two key enhancements: using Lean maturity assessments as a new data source and developing a hybrid forecasting model combining Logistic regression and Neural Network techniques. The proposed methodology is evaluated through a comprehensive empirical study involving 30 teams in a large supply chain company, revealing notable improvements in forecasting accuracy. Compared to a baseline scenario without process improvement data, the new methodology achieves an enhanced accuracy score by 17% and an improved F1 score by 13 %. These findings highlight the benefits of integrating Lean maturity assessments and adopting a hybrid forecasting model, contributing to the advancement of supply chain analytics. By incorporating lean maturity assessments, the forecasting process is enhanced, providing a deeper comprehension of the underlying Lean framework and the impact of its elements on supply chain performance. Additionally, adopting a hybrid model aligns with current best practices in forecasting, allowing for the utilisation of various techniques to optimise KPI prediction accuracy while leveraging their respective strengths.

Keywords

• Supply chain analytics
• Process improvement
• Lean six sigma
• Key performance indicators
• Logistic regression
• Neural networks