Machine learning-based design features decision support tool via customers purchasing data analysis

Abstract

Decision-making on design features such as specifications and components is an essential aspect of new product development. Customers product preferences and their variations provide the basis of design features decision. Big data of product sales are an emerging source for the obtaining of customers preferences on product features. In this work, a machine learning-based design features decision support tool is proposed through big sales data analysis. Customers preferred product features and their combinations are predicted based on the sales data. Physical feasibility of the product features combinations is considered for customers preference analysis. Cluster analysis method is proposed to identify common and alternative design of product features. Based on specification/component relationships, design features decisions of product components are carried out by grouping product component into noncritical, common, and alternative components. A case study on electric toy cars was included to illustrate the effectiveness of the proposed method.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 13 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.