At MX8 Labs, we employ advanced fraud detection techniques to ensure data integrity by identifying and removing fraudulent respondents and automated bots. Our system analyzes multiple signals across user behavior, network activity, and device characteristics to detect anomalies in real time.
Signal Categories
Screening draws on five families of signal, each evaluated in real time as the respondent enters the survey.
- User behavior signals - whether the browser session has been configured or altered to avoid identification, including attempts to conceal, tamper with, or reset the identifiers used to recognize a returning respondent.
- Network signals - whether the connection is consistent with the respondent's reported location, whether the true origin is being masked, and whether the same network is being used repeatedly or switched mid-session.
- Bot detection signals - whether the session shows the characteristics of automated rather than human participation, including scripted browsers and traffic originating from environments built to simulate real devices at scale.
- Device data signals - whether the reported device profile is internally coherent, and whether the device is being operated remotely rather than used directly by the respondent.
- Mobile device signals - whether a mobile device, its operating system, and its app environment are in an unmodified state.
The signals are weighted and combined into a single risk score for each respondent, and respondents whose score exceeds the threshold set for the study are excluded before their data reaches analysis.
We publish the categories rather than the individual signals within them, because the signal-level detail is precisely what a fraud operator would need in order to defeat it. If you need the full inventory for a security review, a procurement questionnaire, or a client audit, contact the MX8 Labs team or see trust.mx8labs.com.
What happens to flagged respondents
Fraud and bot screening is one of several layers of respondent validation. It sits alongside deduplication, in-survey attention and consistency checks, and in-field monitoring - see Data quality methodology for how the layers fit together, and IP Address Hygiene and Exposure Matching for how the same pipeline applies to ad-exposure work.
Respondents excluded by these checks do not appear in your results. They are recorded against your respondent source as Poor Quality, with the specific respondent IDs listed in the Respondent reconciliation download, so you can reconcile delivery with your sample provider on individual IDs rather than on totals alone.
Disabling bot detection
If you are entirely comfortable that everyone entering your survey will be a real human, you can disable bot detection by adding the following to your survey:
s.allow_bots = True
Trusting all respondents on a source
Quality controls can also be relaxed per respondent source. Each editable source has a Trust all respondents toggle:
When enabled, MX8 will not mark respondents from that source as poor quality based on fingerprint bot signals or IP and cookie mismatches. It is off by default, so quality checks apply unless you turn it on. Use it for sources you already trust — for example, an interviewer-administered source or a controlled first-party list — where the standard fingerprint and IP checks would produce false positives.
The toggle appears on sources where it makes sense to configure it, such as panel, first-party, ad-exposure, and integrated panel sources. Sources that are inherently trusted — synthetic, profile synthetic, third-party import, Twilio voice and text, and test links — always trust their respondents and do not show the toggle.