Location
Hilton Waikoloa Village, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
7-1-2025 12:00 AM
End Date
10-1-2025 12:00 AM
Description
Informational consumer friction—resulting from insufficient or overly complex product information—can negatively affect consumer purchase decisions. This paper proposes that monitoring an individual’s digital behavior through mouse dynamics offers a novel method to identify and predict conditions of higher or lower friction. We examine this proposition in an exploratory study that assesses the relationship between informational consumer friction and mouse dynamics. By manipulating the difficulty of evaluating product features, we found that three mouse dynamic metrics—sub-movements, x-flips, and area under the curve—are significantly related to friction conditions. We also developed machine learning models to predict whether individuals were evaluating a product under higher or lower friction conditions and achieved a classification accuracy of over 67%. The findings suggest that digital behavior, particularly mousing dynamics, provides valuable insights that can allow researchers and practitioners to identify informational friction and ultimately enhance consumer experiences.
Recommended Citation
Weisgarber, Paul; Valacich, Joseph; Jenkins, Jeff; Wilson, David; and Kim, David, "Identifying and Predicting Consumer Informational Friction: A Digital Behavioral Biometric Approach" (2025). Hawaii International Conference on System Sciences 2025 (HICSS-58). 3.
https://aisel.aisnet.org/hicss-58/in/hci/3
Identifying and Predicting Consumer Informational Friction: A Digital Behavioral Biometric Approach
Hilton Waikoloa Village, Hawaii
Informational consumer friction—resulting from insufficient or overly complex product information—can negatively affect consumer purchase decisions. This paper proposes that monitoring an individual’s digital behavior through mouse dynamics offers a novel method to identify and predict conditions of higher or lower friction. We examine this proposition in an exploratory study that assesses the relationship between informational consumer friction and mouse dynamics. By manipulating the difficulty of evaluating product features, we found that three mouse dynamic metrics—sub-movements, x-flips, and area under the curve—are significantly related to friction conditions. We also developed machine learning models to predict whether individuals were evaluating a product under higher or lower friction conditions and achieved a classification accuracy of over 67%. The findings suggest that digital behavior, particularly mousing dynamics, provides valuable insights that can allow researchers and practitioners to identify informational friction and ultimately enhance consumer experiences.
https://aisel.aisnet.org/hicss-58/in/hci/3