Researchers have found that machine learning and artificial intelligence (AI) can significantly reduce cost and time in product design (the topic of Chapter 5), not only in the actual generative design of the product, but also in the predictive analysis of whether consumers will be attracted to certain designs.
“It’s well understood in the automotive industry that aesthetics are critically important to market acceptance. An improved aesthetic design has demonstrated that it can boost sales 30% or more,” says a Yale U. prof (see INFORMS.org Dec. 11. 2023). “That’s why automakers are known to invest over $1 billion in the design of a single model.”
The current auto design process relies on the conventional human development of designs and prototypes, along with in-person testing of possible designs with actual consumers. These consumer evaluations feature what is called the A/B testing of alternative designs in laboratory test markets. The industry calls them “theme clinics,” in which hundreds of targeted consumers are recruited and brought to a central location to evaluate aesthetic designs. Consumers are asked to rate the designs based on established benchmarks, such as scales for “sporty,” “appealing,” “innovative” and “luxurious,” among other characteristics.
Auto makers invest more than $100,000 per theme clinic for one new vehicle design. Because there are multiple aesthetic designs per vehicle, and more than 100 vehicles in its product line, General Motors alone, for example, spends tens of millions of dollars just on theme clinics.
Researchers found ways to augment the traditional product development process with machine learning tools that address both the generation of the design itself, and the testing of possible consumer acceptance or rejection of the design. They developed a generative model that creates new product designs and allows designers a tool to morph potential designs more efficiently and effectively. Their predictive model helps identify those designs with high aesthetic scores. They created their models using data from an auto firm, using images of 203 SUVs that were evaluated by targeted consumers, and 180,000 high-quality unrated images.
With advancements in machine learning algorithms and computer vision technology, AI is also capable of predicting safety risks on roads by analyzing data from sensors attached to vehicles.
Classroom discussion questions:
- What does A/B testing mean?
- Why is AI a valuable tool in design of cars–and other consumer products?