AI-Powered Fraud and the Erosion of Online Survey Integrity: An Analysis of 31 Fraud Detection Strategies

Natalia Pinzón, Vikram Koundinya, Ryan Galt, William Dowling, Marcela Boukloh, Namah C. Taku-Forchu, Tracy Schohr, Leslie Roche, Samuel Ikendi and Mark H. Cooper

No 95tka, SocArXiv from Center for Open Science

Abstract: The proliferation of AI-powered bots and sophisticated fraudsters significantly threatens the integrity of online surveys, leading to a substantial decline in usable responses from 75% to 10% in recent years. This study evaluates the efficacy of 31 fraud indicators using two agriculture surveys in California. Our comparative analysis, which integrated multiple methodological innovations, revealed that no single indicator is independently effective. However, best indicators included a novel email address score, MinFraud Risk Score, consecutive submissions, opting-out of incentives, improbable location, and survey start time. Our findings underscore evolving tactics of fraudsters, demonstrating their increased proficiency in responding to matching, domain knowledge, and open-ended questions. Higher monetary incentives attract sophisticated fraudsters capable of mimicking genuine open-ended responses and verifying information provided months prior, showcasing a significant advancement in the capabilities of survey fraud groups. We conclude with recommendations for developing adaptable fraud detection strategies to safeguard survey integrity.

Date: 2023-12-28
New Economics Papers: this item is included in nep-agr and nep-ain
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://osf.io/download/658da5690344614bbc68f579/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:95tka

DOI: 10.31219/osf.io/95tka

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF ().