- Past Event Highlights
- Article
Face Verification as Real-Time Solution for Survey Quality
Mihkel Jäätma – CEO, Realeyes
Scott Jones – VP of Product, Realeyes
Nick Sutton – Chief Strategy Officer, Kantar Profiles
Thirty percent of surveys are fake, based on an analysis of over half a million surveys. Quality issues have been prevalent for a long time now, and there is a need to address this. Survey panel quality has gotten worse because the marketplace does not value quality, fraudsters move faster than researchers and quality issues are not addressed adequately. Previous tools to deal with fraud are insufficient specifically for programmatic sample that is almost 70% of all surveys now. Quality issues are not visible enough, and there is need to create a transparency dashboard that is publicly available. Solution: face verification, which can be a game changer in survey quality. It is real time, cross-supply and simpler than CAPTCHA. The tool is established on properly obtained training data, that is tackling algorithmic bias head on and works everywhere on any device. There are different types of “bad actors”: the disengaged panelist, the dishonest panelist, the fraudulent panelist—the single biggest bad actor is from out of country. Following this there are bots, ghost completes and inconsistent answers (dishonest). There is not one single solution but rather a basket of solutions to make sure the quality is maintained. Key takeaways:- Widespread quality issues and deteriorating survey panel quality is a significant problem.
- Existing tools for detecting and preventing survey fraud are insufficient, particularly for programmatic sample surveys.
- To combat these quality and integrity issues, face verification is suggested. It stands out for being real-time, applicable across different survey supplies and more user-friendly than traditional CAPTCHA methods.
