electricsheepafrica/nigerian-banking-credit-bureau

这是一个生产级别的合成数据集，包含了真实的尼日利亚银行背景信息，旨在用于信用风险建模、信用评估和贷款优化。数据集包含尼日利亚的银行名称、州、人口统计信息，具有机器学习就绪的高风险标签（20%的普遍性），共有200万行数据，覆盖了从2023年1月1日到2024年12月31日的时间段。数据集分为训练集、验证集和测试集，包含了记录ID、客户ID、报告日期、信用评分、总债务（尼日利亚货币）、活跃账户、逾期账户、支付历史月数、信用使用率和高风险等关键列。

This is a production-grade synthetic dataset with authentic Nigerian banking context, designed for credit risk modeling, creditworthiness assessment, and lending optimization. The dataset includes real bank names, states, demographics of Nigeria, with ML-ready high risk flags (20% prevalence), totaling 2,000,000 rows, covering the period from 2023-01-01 to 2024-12-31. It is split into Train, Validation, and Test sets, and features key columns such as record_id, customer_id, report_date, credit_score, total_debt_ngn, active_accounts, delinquent_accounts, payment_history_months, credit_utilization, and high_risk.