Skip to content
  • There are no suggestions because the search field is empty.

Fraud Analysis in Crosschq Interview

How Crosschq Interview detects integrity risks during AI-conducted interview sessions, and how to read the results in the Interview Report.

Note: This article covers Fraud Analysis for Crosschq Interview — which evaluates AI Agent interview sessions. If you're looking for fraud detection in reference checks, see Understanding Fraud Risk in Crosschq 360.

Overview

When a candidate completes an AI Agent interview, Crosschq automatically analyzes the session for signals that may indicate the person who took the interview was not the actual candidate, or that outside assistance was used. The results appear on the Fraud Analysis tab of the Interview Report.

Fraud Analysis is designed to give your team an early signal to investigate further — it does not make a hiring decision automatically.

How to access Fraud Analysis

Open any completed AI Agent interview from Interview Management and select the Fraud Analysis tab. The tab only appears when two conditions are both true:

  • Your organization has fraud detection enabled at the org level.
  • The fraud analysis setting is turned on for the specific interview.

If the tab is missing for some interviews but visible on others, one of those two settings is off for the affected interviews. Contact your Crosschq administrator.

Reading the risk score

At the top of the Fraud Analysis tab, a gradient bar shows the overall risk level for the session, ranging from low risk on the left to high risk on the right.

Risk level What it means
Low Few or no signals detected. The session proceeded without notable integrity concerns.
Medium One or more signals detected that warrant a closer look, but are not conclusive on their own.
High Multiple or significant signals detected. Review the signal groups and consider following up with the candidate before advancing them.
Important: A high risk score does not confirm that fraud occurred. It means the session produced patterns worth reviewing. Always look at the full picture — responses, scorecard, and other information — before making a decision.
 

Signal groups

Below the risk bar, the tab shows signal groups — categories of signals Crosschq evaluates during each interview. Each group is rated independently.

Signal group What it evaluates
Audio Consistency Whether the voice in the session was consistent throughout, or patterns suggest a different speaker at different points.
Identity Signals Whether the person on screen matches the candidate's expected identity.
Response Patterns Whether responses suggest the candidate was answering naturally, or reading from a script or receiving outside assistance.
Session Behavior Technical signals such as unusual pauses, tab switches, or behaviors inconsistent with a normal interview environment.

How to act on results

  • Low risk: No action required. Continue your normal review.
  • Medium risk, single group flagged: Review the signal group description. Many medium signals have benign explanations. Use your judgment alongside the rest of the report.
  • High risk or multiple groups flagged: Consider reaching out to the candidate to verify their identity before advancing them in the process.

How this differs from Crosschq 360 fraud detection

Crosschq Interview Crosschq 360
What it analyzes The AI Agent interview session — video, audio, session behavior Reference check responses — identity, contact details, shared devices
Who it flags The candidate (was the person really who they claim to be?) References and candidates (are the references real?)
Where it appears Fraud Analysis tab in the Interview Report Response Analysis section of the Crosschq 360 report