Using Machine Learning for Product Portfolio Management: A Methodical Approach to Predict Values of Product Attributes for Multi-Variant Product Portfolios

Abstract

To satisfy customer needs in the best way, companies offer them an almost infinite number of product variants. Although, an identical product was not built before, the values of its attributes must be determined during the product configuration process. This paper introduces a methodical approach to predict the values of product attributes based on customer feature configurations using machine learning. Machine learning reduces the effort compared to rule-based expert systems and is both, more accurate and faster. The approach was validated by predicting vehicle weights using industrial data.

Methodical Approach to Cluster Configurations of Product Variants of Complex Product Portfolios

“…The number is much higher for commercial vehicles (Kusiak et al, 2007). Although the complexity is no longer manageable manually, the activities in product portfolio and variety management are driven by the experiential knowledge of the developers (Mehlstäubl, Braun, et al, 2022). Machine learning techniques offer great potential in these disciplines and make it possible to gain insights from large amounts of data and thus provide a meaningful basis of information for decision-making processes in product portfolio and variety management (Mehlstäubl et al, 2023).…”