GEO: A computational design framework for automotive exterior facelift

Huang, J., Chen, B. , Yan, Z., Ounis, I. and Wang, J. (2023) GEO: A computational design framework for automotive exterior facelift. ACM Transactions on Knowledge Discovery from Data, 17(6), 82. (doi: 10.1145/3578521)

Abstract

Exterior facelift has become an effective method for automakers to boost the consumers’ interest in an existing car model before it is redesigned. To support the automotive facelift design process, this study develops a novel computational framework – Generator, Evaluator, Optimiser (GEO), which comprises 3 components: a StyleGAN2-based design generator that creates different facelift designs; a convolutional neural network (CNN)-based evaluator that assesses designs from the aesthetics perspective; and a recurrent neural network (RNN)-based decision optimiser that selects designs to maximise the predicted profit of the targeted car model over time. We validate the GEO framework in experiments with real-world datasets and describe some resulting managerial implications for automotive facelift. Our study makes both methodological and application contributions. First, the generator’s mapping network and projection methods are carefully tailored to facelift where only minor changes are performed without affecting the family signature of the automobile brands. Second, two evaluation metrics are proposed to assess the generated designs. Third, profit maximisation is taken into account in the design selection. From a high-level perspective, our study contributes to the recent use of machine learning and data mining in marketing and design studies. To the best of our knowledge, this is the first study that uses deep generative models for automotive regional design upgrading and that provides an end-to-end decision-support solution for automakers and designers.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Huang, Mr Jingmin and Ounis, Professor Iadh and Chen, Dr Bowei
• Authors: Huang, J., Chen, B., Yan, Z., Ounis, I., and Wang, J.
• College/School: College of Science and Engineering > School of Computing Science; College of Social Sciences > Adam Smith Business School > Management
• Journal Name: ACM Transactions on Knowledge Discovery from Data
• Publisher: Association for Computing Machinery
• ISSN: 1556-4681
• ISSN (Online): 1556-472X
• Published Online: 27 December 2022
• Copyright Holders: Copyright © 2022 Association for Computing Machinery
• First Published: First published in ACM Transactions on Knowledge Discovery from Data 17(6): 82
• Publisher Policy: Reproduced in accordance with the publisher copyright policy