Shop - E-commerce Anti-Fraud Data Scientist

Position: TikTok Shop - E-commerce Anti-Fraud Data Scientist
About the Team:
As part of the Governance and Experience (GNE) organization, our Risk Control and Security team safeguards Tik Tok Shop's global marketplace for users, sellers, and creators. We blend data-driven insights, policy design, and technical innovation to combat fraud while preserving a seamless user experience. The E-commerce Anti-Fraud Data Scientist role sits at the intersection of defining success metrics system, risk analytics, and cross-functional collaboration to monitor and mitigate fraudulent activities.

Responsibilities:

* Define, standardize and monitor key performance metrics, building robust reporting models for effective tracking, evaluation, and continuous improvement

* Conduct deep-dive RCA for fraud metric anomalies, collaborate with product/algo/engineering teams to optimize detection mechanism, and deliver actionable mitigation actions.

* Design A/B experiments to evaluate model/strategy effectiveness, calculate ROI of anti-fraud initiatives, and scale high-impact solutions across global markets.

* Leverage AI driven approaches to build and iterate scalable tooling to facilitate monitoring and analytics.

* Lead cross-functional projects to address findings and present insights to key stakeholders and manage timeline of key projects.

Minimum Qualifications:

* Bachelor's degree or above in Mathematics, Statistics, Computer Science, Business Analytic, or related fields (or post-graduation experience in data modeling/analysis).

* Proficient in SQL and Tableau; skilled in Python/R for data analysis, model building, and visualization.

* Strong ability to process complex datasets, identify fraud patterns, and translate insights into business actions.

* Problem-solving skills to address evolving fraud challenges.

Preferred Qualifications:

* E-commerce anti-fraud experience (e.g., transaction fraud detection, ATO prevention).

* Global market analysis experience or cross-regional project leadership experience.

* Experience with ML model lifecycle management (training, deployment, monitoring) and A/B experiment design for risk initiatives.

* Experience with AI based analytics tooling is preferred.