Fraud Data Analyst

What you'll do:

• Investigate and Develop Fraud Detection Strategies. Conduct thorough investigations of fraud attacks, identify potential detection leads, and collaborate with engineering teams and data scientists to design, develop, and roll out new detection models and capabilities and expand our signal collection variety.
• Leverage Data for Actionable Insights. Apply data-driven techniques to analyze fraud patterns, generating insights that enhance our detection strategies and customer outcomes.
• Develop Tools for Efficiency and Reporting. Create tools to streamline investigations, improve report generation, and boost overall product efficiency.
• Educate and Train External Teams. Lead training sessions and onboarding for external teams, equipping them with knowledge of emerging threats and our product’s capabilities.
• Provide Expert Customer Support. Support customers by addressing complex fraud scenarios and helping them effectively use our platform to mitigate risks.

Who you are:

• Technical Proficiency:
SQL (Must-have): Essential for querying and manipulating large datasets.
Python (can be on an intermediate level): Key for scripting, data analysis, and model development.
Data Visualization Tools (Looker, ReDash): Ability to visualize data effectively to communicate insights.
Excel: Advanced skills for data analysis and reporting.
• Analytical and Research Skills:
Statistical Methods: Strong understanding of statistical techniques to analyze and interpret data.
Research Methodology: Ability to design and conduct research to uncover fraud patterns and trends.
KPI Management (FP/FN): Ability to monitor and optimize key performance indicators like false positives and false negatives.
Data Storytelling: Ability to use data to tell a compelling story, going beyond just presenting data to provide actionable insights.
• Cybersecurity and Data Science Knowledge:
Fraud Expertise: A deep understanding of the fraud landscape and the attacker’s mindset.
Familiarity with Cybersecurity Concepts: Understanding of HTTP and web architecture, cookies, etc.
Knowledge of Data Science: Familiarity with models, networks, and data science practices (advantageous but not required).
• Additional Skills:
Passion and Innovation: A genuine interest in fraud prevention, with a willingness to innovate and get hands-on with challenging problems.
Collaboration and Knowledge Sharing: Strong teamwork skills and the ability to share insights and knowledge across the team.