Senior Data Scientist

• Review suspicious activity and complex fraud cases to help identify and resolve fraud risk trends and issues. Clearly and thoroughly document investigation findings and conclusions. Understand how to write rules in LexisNexis decision engines and manage customer risk policy, leveraging hundreds of signals in LexisNexis Digital Identity Network and data fed directly into the network by our customers. Offline analyses of customer data to tune rules, exposes patterns, research anomalies, reduce false positives, and build executive and project-level reports. Identify meaningful insights from chargeback data. Interpret and communicate findings from analysis to engineers, product and stakeholders. Analyze high-volume data to investigate, identify and report trends linked to fraudulent transactions. Collaborate with LexisNexis teams including Products, Engineering, and colleagues to continually redefine best practices by enhancing tools, data sources, system functionalities, and fraud detection methods. Educate internal team members and external parties on processes and procedures. Demonstrate a professional and customer-centric persona when interacting directly with merchants and customers via on-site visits, phone, e-mail, and chat. Risk and Technology consulting; sharing best practices with fraud managers, risk analysts, application developers, and project managers for combating persistent and emerging security threats. Perform other duties as needed.

• Master’s degree (or foreign equivalent) in Data Science, Computer Science, Business Analytics, Information Systems, or a related field required.

• 3 years of experience in job offered or related occupations required.

• Also required is: 3 years of experience: in technical suite, including python (numpy, Pandas, sci-kit learn), SQL, cloud services (Snowflake), Jupyter Notebooks, collaboration tools like Git and BitBucket, visualization tools like Matplotlib, Tableau or PowerBI, and IDE experience (Visual Studio Code); with machine learning modelling, overall modelling pipeline, and Feature Engineering, including supervised learning (logistic regression, XG Boost, LGBM), anomaly detection, clustering, graph analysis, feature engineering and data preprocessing, performance metrics like accuracy, precision, recall, F1, AUC-ROC, AUC-PR, and model governance documentation; clearly and effectively communicating to convey complex data insights and analysis results to clients who may not have a technical background; applying analytical thinking to understand client issues and propose tailored solutions that leverage the our solutions and capabilities to help prevent fraud and provide a seamless customer experience; understanding various types of fraud (e.g., credit card fraud, identity theft, phishing, stolen credentials fraud, first party fraud), familiarity with industry-specific fraud schemes, such as insurance fraud or banking fraud, and awareness of emerging fraud trends and techniques that fraudsters use; conducting thorough risk evaluations to determine the impact, likelihood, and scope of potential fraud incidents; using data analysis to identify patterns or anomalies that might indicate potential risks; and understanding how to balance fraud prevention measures with the need for a positive user experience.

• Employee reports to LexisNexis Risk Solutions FL, Inc. office in New York, NY, but may telecommute from any location within the U.S.
• Experience can be concurrent.

SALARY RANGE FOR REQ# R115156