An analytical model for analyzing the value of information flow in the production chain model using regression algorithms and neural networks

Abstract

Managing information flow has always been a challenging and critical driver of performance increase in manufacturing companies. Each bit of information related to the manufacturing process has an information flow value that can impact the process. Recent studies have focused on the traditional classification algorithms methods to analyze the value of information flow. In this research paper, we use regression algorithms to develop an analytics model for the value of information flow in manufacturing shop floors of developing countries. The analysis shows that the Artificial Neural Network (ANN) has the best regression coefficient score of 0.775 with a prediction error of 0.0125. The lowest regression coefficient score of 0.323 was for the Multi-Linear Regression (MLR) with a prediction error of 0.0556. These results help companies use regression algorithms effectively to analyze the value of information flows on the manufacturing chains.

Keywords

• Artificial neural network
• Information flow management
• Regression algorithms
• Value of information
• Production chain model