Home // CENTRIC 2015, The Eighth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services // View article

Rating Decomposition with Conjoint Analysis and Machine Learning

Authors:
Florian Volk
Nadine Trüschler
Max Mühlhäuser

Keywords: product ratings; decomposition; conjoint analysis; machine learning; classification; product quality; supplier selection.

Abstract:
When customers leave feedback about products, for example, a rating, they often evaluate a product as monolithic unit, neglecting that products are composed of parts with different quality, often delivered by independent suppliers. Manufacturers are more interested in individual ratings for product parts than in an overall rating. With decomposed ratings, manufacturers can improve the product quality, the selection of suppliers, and adapt pricing strategies. In this paper, we present an automated approach to decompose overall product ratings into individual ratings for product parts by the use of the results of a Conjoint analysis and supervised machine learning. Using this approach, individual ratings for product parts can be predicted with a high accuracy.

Pages: 36 to 41

Copyright: Copyright (c) IARIA, 2015

Publication date: November 15, 2015

Published in: conference

ISSN: 2308-3492

ISBN: 978-1-61208-440-4

Location: Barcelona, Spain

Dates: from November 15, 2015 to November 20, 2015