A rating method for improved accuracy of customer evaluations and cost savings
Princeton Docket # 20-3660
With the rise of analytics, good data is essential in today’s environment. Researchers in the Department of Sociology at Princeton University and in the Department of Psychology at Hunter College have developed a virtual rating method that associate online ratings with differential time costs by endowing the graphical user interface that solicit ratings from users with interactive “physics,” including an intuitive sliding scale with friction. When ratings are associated with differential time cost, scores correlate more strongly with objective service quality. Implementing this novel strategy lowers the sample size, and costs required for obtaining reliable, crowd analytic information. Our method improves the information quality obtained in online rating and feedback systems. Endowing a rating widget with virtual physics increases the time cost for reporting extreme scores obtaining more accurate crowd estimates. Implications include improving accuracy of evaluations in e-commerce, workforce review and development, and business development together with cost savings in fewer product returns and in reputation costs by reducing customer dissatisfaction. This approach can be generalized and tested in a variety of large-scale online communication systems.
Present technology aims at minimizing client efforts in reporting feedback. This method solves the problem of low quality information in rating systems, where distribution of reports tend to extremes. In current Star ratings for example, the high variance caused by many 1 Star and 5 Star ratings obscure the ground truth
-Customer Service Ratings
-More Accurate Data
-Smaller Sample Size
-Adjustable Screening Parameters
-Based on Cost Signaling Theory
Intellectual Property & Development Status
Patent protection is pending.
Princeton is currently seeking commercial partners for the further development and commercialization of this opportunity.
Ofer Tchernichovski, Lucas C. Parra, Daniel Fimiarz, Arnon Lotem, Dalton Conley (2019). Crowd wisdom enhanced by costly signaling in a virtual rating system. Proceedings of the National Academy of Sciences March 2019, 201817392; DOI:10.1073/pnas.1817392116
Dalton Conley is the Henry Putnam University Professor in Sociology. He holds PhDs in both sociology and biology. Conley’s scholarship has primarily dealt with the intergenerational social and genetic transmission of socioeconomic and health status from parents to children. He has been the recipient of Guggenheim, Robert Wood Johnson Foundation and Russell Sage Foundation fellowships as well as a CAREER Award and the Alan T. Waterman Award from the National Science Foundation. He is an elected fellow of the American Academy of Arts and Sciences and an elected member of the National Academy of Sciences.
Ofer Tchernichovski is Professor of Psychology, Hunter College, City University of New York. A Ph.D. in zoology, he uses the songbird to study mechanisms of vocal learning. Like early speech development in the human infant, the songbird learns to imitate complex sounds during a critical period of development. His lab studies the animal behavior and dynamics of vocal learning and sound production across different brain levels. The lab aims to uncover the specific physiological and molecular (gene expression) brain processes that underlie song learning.
Princeton University Office of Technology Licensing