1,000 transaction-level fraud cases from India's Unified Payments Interface (UPI) system. The dataset covers the fiscal years 2023 to 2025, providing a snapshot of fraudulent activity within a major digital payment network. Its origin and specific collection method are unknown.
Use Cases
- Train fraud classification models based on transaction-level case data.
- Analyze temporal patterns of UPI fraud based on the FY2023–FY2025 coverage.
- Benchmark fraud detection algorithms using a collection of real-world cases.
Strengths
- Contains 1,000 individual fraud cases.
- Focuses on a specific payment system (UPI) and geography (India).
- Has a defined temporal coverage of fiscal years 2023 to 2025.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Time Range
- FY2023–FY2025
- Geography
- India