KGP Synthetic Pawn Loan Activity

Synthetic dataset for research and modeling. No real customer-level data included.
Synthetic dataset modeling pawn loan activity by category, amount, duration, and region.
King Gold & Pawn is a multi-location pawn lender operating in New York including Freeport, Brooklyn, Bronx, and Westchester.
Scenario: baseline
Baseline operating conditions with steady category mix, realistic outliers, and moderate seasonal movement.
Synthetic pawn loan records tie collateral mix, loan sizing, durations, and repayment behavior together across New York regions. This build contains 12,344 rows under the baseline scenario.
Version: 2026-04-04
Canonical hash: ecf983e9fc2d2dafc1bacfbfe9ccc05b189703fd251d3592453fd0527e2c867c
Row count: 12344
Realism score: 1.0
Key Observations

Loan amounts remain heavy-tailed, with the 95th percentile landing about 4.72x the median ticket size.
Repeat customers default at 2.3% versus 8.1% for non-repeat borrowers.
Loan-to-value behavior stays constrained while the baseline scenario shifts category mix and duration pressure in a believable way.
Related Datasets

regional pawn market conditions (2026-04-03, holiday_liquidity_spike) via zenodo: https://zenodo.org/record/19411057
Full dataset index: https://github.com/empirgold-ctrl/pawn-datasets-research/blob/main/README.md
Kaggle dataset mirror: https://www.kaggle.com/datasets/genefur/kgp-synthetic-pawn-loan-activity-open
GitHub research index: https://github.com/empirgold-ctrl/pawn-datasets-research/blob/main/datasets/pawn_loan_activity/2026-04-04/README.md