Paper Type

Complete

Abstract

Various disruptive events, such as the COVID-19 pandemic are creating a highly unstable and turbulent economic environment and thus significant challenges for corporate planning. The use of modern machine learning methods can be an approach to improving and expanding operational planning in dynamic markets. Current studies show a low success rate in the development and use of AI applications. The critical factors for the failure of these projects are largely due to inadequate methodology or a lack of process models. Existing process models are not sufficient to provide detailed assistance in the development of operational AI applications. The aim of the paper is to develop a framework for a structured approach to a dynamic forecasting model, called predictive intelligence, in order to meet challenges in the application of artificial intelligence. The framework is validated by a case study on forecasting customer orders with sporadic demand and unknown supply chains.

Paper Number

1209

Comments

SIGDSA

Share

COinS
Top 25 Paper Badge
 
Aug 16th, 12:00 AM

PREDICTIVE INTELLIGENCE USING THE EXAMPLE OF FORECASTING CUSTOMER ORDERS IN THE METALWORKING INDUSTRY

Various disruptive events, such as the COVID-19 pandemic are creating a highly unstable and turbulent economic environment and thus significant challenges for corporate planning. The use of modern machine learning methods can be an approach to improving and expanding operational planning in dynamic markets. Current studies show a low success rate in the development and use of AI applications. The critical factors for the failure of these projects are largely due to inadequate methodology or a lack of process models. Existing process models are not sufficient to provide detailed assistance in the development of operational AI applications. The aim of the paper is to develop a framework for a structured approach to a dynamic forecasting model, called predictive intelligence, in order to meet challenges in the application of artificial intelligence. The framework is validated by a case study on forecasting customer orders with sporadic demand and unknown supply chains.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.