In the banking sector, machine-learning methods are applied in a wide variety of business areas: assessing a client’s risk profile (application and behavior scoring), forming targeted sales (x-sell, up-sell), choosing collection strategies (collection scoring), etc. The bank anti-fraud division is no exception, where with the help of machine-learning methods effective anti-fraud tools are developed. This paper deals with B-tests: methods by which it is possible to identify internal fraud among employees and partners of the bank at an early stage.

中文翻译：

---

预测欺诈分析：B 测试

在银行业，机器学习方法应用于广泛的业务领域：评估客户的风险状况（申请和行为评分）、形成目标销售（x-sell、up-sell）、选择收款策略（收款评分） ) 等。银行反欺诈部门也不例外，在机器学习方法的帮助下，开发了有效的反欺诈工具。本文涉及 B 测试：可以在早期识别银行员工和合作伙伴之间的内部欺诈的方法。