Transaction Details
Result
Fill in the details and run analysis
Fraud by category
Fraud by hour of day
Transaction distribution
Algorithm comparison (ROC-AUC)
Recent flagged transactions
| ID | Card | Amount | Category | Hour | Score | Status |
|---|
Algorithm
Random Forest — 100 decision trees vote on each transaction. Majority wins. Doesn't overfit like a single decision tree would.
Class Imbalance
Fraud is rare (~3%). SMOTE creates synthetic fraud samples during training so the model doesn't just say "always legit."
Feature Importance
Metrics
Pipeline
The team behind FraudShield — SKIT Jaipur, CSE Batch 2023