Date of Publication :17th January 2024

Abstract: The article examines applications of AI algorithms in the field of procurement and sourcing. Based on a common project with a German enterprise the use of machine learning methods to determine the price of purchased parts and components will be presented and discussed. The project implementation is described in detail using the CRISP procedure model. The price estimates of the AI model can be used in particular for new products. Although there is not any quotation for a new product we can estimate how much should it cost at the procurement market by our machine learning model. When price negotiations with suppliers begin, the responsible purchaser has received helpful information on the expected or target price and can therefore better evaluate any offers from the potential supplier. An innovative two-stage technique with Clustering and Artificial Neural Nets showed the best results. The basis for this approach is a large data collection of previously supplied components with their specifications and their procurement prices. Additionally to the price forecast one get the most important price and delivery cost driver so it gives some hints for reducing the delivery price or to control the negotiation process.

Reference :