Presentation

Presentation: MSI Webinar: Screening Consumer Complaints for Safety Concerns: A Topic Model for Decision

Jia Liu

Hong Kong University of Science and Technology

Apr 25, 2025

Consumer complaints often signal product recalls, but firms and regulators struggle to track patterns due to limited resources and unstructured data.
To solve this, we developed an AI-driven model (HDPYP) that analyzes complaints in real time, identifying defect trends and predicting recall risks. Applied to the U.S. auto industry, this approach helps manufacturers proactively address issues, reduce losses, and improve safety. Regulators can better prioritize complaints, speed up investigations, and ensure recall notices reflect real consumer concerns—all with minimal manual effort.
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.