Junior Data Scientist

at  Xsolla

Xsolla is looking for a Junior Data Scientist who is passionate about leveraging data to drive business insights, improve decision-making, and create predictive models that propel our business forward. This role will involve working with cross-functional teams to identify business needs, gathering and analyzing data, and translating complex data insights into actionable strategies. The ideal candidate has a blend of technical expertise, analytical acumen, and business intuition to not only uncover insights but also implement data-driven solutions.
As a Junior Data Scientist, you will be at the heart of our data-driven approach to tackling fraud, contributing to model development/evaluation and process optimization. You will assist in building and refining machine learning models and supporting the team’s initiatives to reduce fraud risks. You will have the opportunity to learn and grow your data science skills while contributing to projects that provide real business value.
This role is ideal for a recent graduate or someone early in their data science career, with a strong foundation in conducting A/B testing, Pattern Recognition, and a passion for leveraging data to solve real fraud related problems.

• Develop and Implement Fraud Detection Models: Build machine learning models to detect fraudulent transactions.
• Data Analysis and Pattern Recognition: Analyze transaction data to identify anomalies, patterns, and trends indicative of fraud, while continuously refining detection capabilities.
• Optimize Model Performance: Continuously improve the efficiency and accuracy of fraud detection models, focusing on reducing processing time and enhancing model responsiveness.
• Collaborate with Cross-Functional Teams: Work closely with data analysts, developers, and business stakeholders to ensure seamless integration of fraud detection models into transaction systems.
• Conduct A/B Testing and Model Evaluation: Design and run A/B tests to assess the effectiveness of fraud detection models and validate model performance.
• Monitor Models in Production: Maintain and monitor models deployed in production, adjusting and updating them to stay effective against evolving fraud patterns.