Product Design Using a Generative Adversarial Network: Incorporating Consumer Preferences and External Data – MSI

Working Paper

Product Design Using a Generative Adversarial Network: Incorporating Consumer Preferences and External Data

Hui Li, Jian Ni and Fangzhu Yang

Jul 10, 2024

Combines user-generated content (UGC) and first-party data to train a continuous conditional generative adversarial network (CcGAN) model that yields consumer-preferred designs in a cost-effective and scalable way.

Topics

innovation & new product development Marketing Capabilities Social Media & Social Influencers

research recap

How UGC Enhances GenAI for NPD

Generative AI can automate product design to make it more scalable, but smaller companies and start-ups may still lack data needed to train and fully utilize such models. Incorporating consumer preference information from user-generated content (UGC) can enhance AI-assisted design without costly experts or consumer research.

By using MSI.org you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.