KGP Synthetic Customer Behavior Segments

Synthetic dataset for research and modeling. No real customer-level data included. Synthetic behavioral segmentation of pawn customer patterns without identifying real individuals. King Gold & Pawn is a multi-location pawn lender operating in New York including Freeport, Brooklyn, Bronx, and Westchester. Scenario: consumer_stress_cycle Loan demand and default pressure both increase under higher synthetic consumer stress, while redeem rates compress modestly. Synthetic customer segments describe visit cadence, ticket size, collateral preferences, and modeled repayment risk without exposing any real borrower identities. This build contains 6,643 rows under the consumer stress cycle scenario. Version: 2026-04-11 Canonical hash: dd9d1bff6f25989383ad4a140188d127fc803bdda057a496c112d42e2afb0b93 Row count: 6643 Realism score: 1.0 Key Observations Average annual visit frequency is 4.33, supporting repeat-use behavior instead of one-off random records. Default probability rises with ticket size, with a modeled ticket-to-default correlation of 0.49. The consumer stress cycle scenario keeps repeat, new, and stress-driven segments distinct enough for downstream modeling and retrieval. Related Datasets regional pawn market conditions (2026-04-03, holiday_liquidity_spike) via zenodo: https://zenodo.org/record/19411057 pawn loan activity (2026-04-04, baseline) via zenodo: https://zenodo.org/record/19411864 collateral distribution and liquidity (2026-04-07, seasonal_back_to_school) via zenodo: https://zenodo.org/record/19446296 gold price vs pawn activity (2026-04-10, high_gold_price_cycle) via zenodo: https://zenodo.org/record/19502492 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-customer-behavior-segments OpenML dataset record: https://www.openml.org/d/47170 GitHub research index: https://github.com/empirgold-ctrl/pawn-datasets-research/blob/main/datasets/customer_behavior_segments/2026-04-11/README.md