Carson Leung

During Trulioo's hypergrowth phase, 工程和客户成功团队在跟上全球400多家数据供应商的步伐方面遇到了问题. Each vendor had its unique maintenance schedule, downtimes, and other disruptions. 该公司只有在性能下降对客户造成长时间影响时才会做出反应. Often, 这导致了数千次KYC失败，以及人工入职带来的数万美元收入损失.

In response, I spearheaded the design, development, 维护早期预警系统，主动扫描所有数据供应商和关键客户，以防止公司旗舰产品的中断. The system immediately notifies the customer success, engineering, and management teams with a call to action if anomalies are detected. By automatically switching affected data sources to backup data vendors, this system prevented disruptions and minimized the impact on customers. This system made our team proactive instead of reactive, which was pivotal in securing larger customer contracts and expansion.

In Jumio, 我整合的业务部门负责开发Jumio事务监控系统，就像公司内部的初创公司一样. 当时，它的数据库针对快速写入进行了优化，但在读取和更新记录方面却非常不理想. Because of this, there was a lack of business intelligence infrastructure and data consistency, 这成为任何平台范围的数据分析和构建预测模型的明显障碍.

I designed the architecture for a high-performance, serverless database that seamlessly integrated with the existing AWS components. Because the database was serverless, it was also extremely low cost. With this database, we developed ETL pipelines for further data refinement, 哪一个启用了商业智能指示板，并将数据质量提高到预测建模的阈值以上.

另一个依赖于数据库的关键业务功能是反洗钱事件记录保存, 提供元分析和快速获取客户潜在欺诈事件，并使统计数据能够向上游监管机构报告.

万事达卡有一个非常先进的生物识别模型，可以推导和分析400多个用户的网络行为特征. 数据点包括设备设置、地理位置和一个人在键盘上打字的独特方式. Everything was combined to create a user's fingerprint, then helped determine whether a user was exhibiting a known or unknown behavior. 如果用户表现出异常行为，其流量将通过不可能的验证码停止. The problem was there could be multiple users within an account. If not distinguished, the behavior of numerous users would be grouped, 从而大大降低了模型判断行为是否异常的能力.

我与数据科学和数据工程合作开发了一个新的规则集，使模型能够识别流量并将其划分为主要流量, secondary, and unknown user behaviors within one account. 这降低了该公司许多重要客户的误报率，有时高达12%. 它最终被其电子商务市场客户采用为主要的欺诈检测方法.