Key Responsibilities
- Design and implement fraud prevention strategies tailored to the specific risks and challenges of online payment transactions.
- Conduct thorough analyses of transactional data to identify patterns, trends, and anomalies indicative of fraudulent activity.
- Collaborate with data scientists and engineers to develop and deploy machine learning models and algorithms for fraud detection.
- Monitor Objectives and Key Results (OKR) related to fraud detection and prevention, and proactively adjust strategies to optimize effectiveness.
- Work closely with operation team to investigate suspected fraudulent transactions and take appropriate action.
- Generate reports and communicate findings to management, highlighting areas of concern and proposing actionable recommendations for improvement.
- Contribute to the construction and enhancement of our fraud platform, aiming to bolster fraud detection capabilities, while also fortifying the system's scalability and flexibility.
- Stay updated on emerging trends and technologies in fraud detection and prevention, and incorporate best practices into our processes and systems.
Qualifications
- 8+ years’ experience in fraud prevention or risk management.
- Master’s degree in a relevant field such as Computer Science, Data Science, Mathematics, or Statistics.
- Strong analytical skills with the ability to interpret complex data sets and draw actionable insights.
- Experience working in fast-paced and rapidly changing working environment.
- Proficiency in data analysis tools and programming languages such as Python, R, SQL, etc.
- Familiarity with machine learning techniques and algorithms for fraud detection (e.g., logistic regression, decision trees, random forests, neural networks, isolation forests, etc.).
- Excellent communication skills with the ability to effectively collaborate with cross-functional teams.
- Detail-oriented and self-motivated with a strong commitment to quality and continuous improvement.
- Experience with payments (particularly working with credit cards) is preferred