AAIA · Question #53
In order to streamline operations, a bank has deployed an AI application to automatically detect and prevent further fraud on accounts. However, customers have voiced concerns that their usual transac
The correct answer is D. The hyperparameters are not optimized.. False positives in a fraud detection model mean the system is incorrectly classifying legitimate transactions as fraudulent. Hyperparameters are the configuration settings that govern how a model learns and makes decisions-such as decision thresholds, regularization strength, and
Question
In order to streamline operations, a bank has deployed an AI application to automatically detect and prevent further fraud on accounts. However, customers have voiced concerns that their usual transactions are being rejected. Which of the following is the MOST likely cause of the false positives?
Options
- AConsent is not properly managed.
- BData versioning controls were not developed.
- CCompute scale training was not performed.
- DThe hyperparameters are not optimized.
How the community answered
(47 responses)- A4% (2)
- B9% (4)
- C13% (6)
- D74% (35)
Explanation
False positives in a fraud detection model mean the system is incorrectly classifying legitimate transactions as fraudulent. Hyperparameters are the configuration settings that govern how a model learns and makes decisions-such as decision thresholds, regularization strength, and learning rates. When hyperparameters are not properly optimized (tuned), the model can become overly sensitive, flagging normal behavior as suspicious. This directly causes false positives. The other options are not the most likely root cause: consent management (A) affects legal compliance, not prediction accuracy; data versioning (B) relates to tracking dataset changes; and compute scale training (C) refers to the hardware resources used, not the model's calibration or sensitivity.
Topics
Community Discussion
No community discussion yet for this question.