Credit Card Fraud Detection

Client Model

Machine learning model to detect fraudulent credit card transactions trained to minimise false positives and consequent loss of transaction fees

Client Model Prediction

Predicted ClassFraud
Model Confidence90%
R-Squared0.66
Significance0.0001

DC-MINT – AI EXPLAINABILITY

  • The transaction was classed as “Fraud”
  • The top three contributing factors towards the ‘Fraud’ prediction were – Amount, Transaction area code and Card registration area code
  • Identify which inputs were causing a higher rate of false positives for model developers
  • A complimentary toolkit to augment the existing model development pipeline for model developers

DC-MINT INSIGHT