Design and Evaluation of Product Aesthetics: A Human-Machine Hybrid Approach

47 Pages Posted: 19 Jul 2019 Last revised: 3 Mar 2021

Date Written: January 2021

Abstract

Aesthetics are critically important to market acceptance. In the automotive industry, an improved aesthetic design can boost sales by 30% or more. Firms invest heavily in designing and testing aesthetics. A single automotive “theme clinic” can cost over $100,000, and hundreds are conducted annually. We use machine learning to augment human judgment when designing and testing new product aesthetics. The model combines a probabilistic variational autoencoder (VAE) and adversarial components from generative adversarial networks (GAN), with modeling assumptions that address managerial requirements for firm adoption. We train and evaluate our model with industry data from an automotive partner—203 SUV images evaluated by targeted consumers and 180,000 high-quality unrated images. Our model predicts well the appeal of new aesthetic designs—43.9% improvement relative to a baseline and substantial improvement over both conventional machine learning models and pretrained deep learning models. New automotive designs are generated in a controllable manner. We empirically verify that automatically generated designs are (1) appealing to consumers, (2) identify designs introduced to the market in the future, and (3) spark creativity to help designers and management explore visual dimensions that affect aesthetic perception. The results suggest that machine learning offers significant opportunity to augment aesthetic design.

Keywords: Aesthetics, Generative Adversarial Networks, Generating New Products, Machine Learning, Prelaunch Forecasting, Product Development, Variational Autoencoders.

Suggested Citation

Burnap, Alex and Hauser, John R. and Timoshenko, Artem, Design and Evaluation of Product Aesthetics: A Human-Machine Hybrid Approach (January 2021). Available at SSRN: https://ssrn.com/abstract=3421771 or http://dx.doi.org/10.2139/ssrn.3421771

Alex Burnap (Contact Author)

Yale School of Management ( email )

165 Whitney Avenue
New Haven, CT 06511
United States

John R. Hauser

MIT Sloan School of Management ( email )

International Center for Research on the Mngmt Tech.
Cambridge, MA 02142
United States
617-253-2929 (Phone)
617-258-7597 (Fax)

Artem Timoshenko

Kellogg School of Management, Northwestern University ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Do you want regular updates from SSRN on Twitter?

Paper statistics

Downloads
578
Abstract Views
2,397
rank
65,254
PlumX Metrics