Manager: Data Science (Credit Card – Fraud/Risk model) @ Visa

Principal Responsibilities

• Work entails heavy focus on developing and implementing best-in-class risk analytic solutions, inclusive of scoring and non-scoring models. Create and deliver powerful insights from data through better visualization and storyboarding

• Work with a broader team that consists of Business Managers, Consultants and Data Scientists from both Visa and client organizations to strategize, co-create, deploy and reap the benefits of data-driven solutions

• Work with regional and global Data Science teams to develop high-quality analytic products and solutions that promote Visa’s growth  in the region

• Keep Visa at the forefront of technological advancement in Data Science by introducing cutting-edge tools and techniques for generating business insights

• Ability to quickly understand and process alternate/non-conventional data sources/platforms and develop AI based advanced prediction algorithms

• Develop next-generation analytic methods where existing tools and techniques are inadequate to address business challenges

• Collaborate with internal Technology partners and Data Engineering function to best leverage Visa’s internal technology platforms, data, and the broader Visa ecosystem to support our clients’ technical data needs

• Manage workload for self and any direct reports, providing prioritization guidance for project flow to improve process efficiency

• Develop, share, and build global best practices and knowledge management within the team

• Socialize innovative ideas and approaches that are scalable and have market demand

• Champion internal requirements around Model Risk Management, Visa Analytics Rules, and Global Privacy standards around client delivery to ensure that Visa’s highly regarded market standing is maintained

This is a hybrid position. Hybrid employees can alternate time between both remote and office. Employees in hybrid roles are expected to work from the office 2-3 set days a week (determined by leadership/site), with a general guidepost of being in the office 50% or more of the time based on business needs.

Professional Experience
• Minimum of 6 years of expertise in applying Machine Learning solutions to business problems – model development and production experience required
• Post-graduate degree (Masters or PhD) in a quantitative field such as Statistics, Mathematics, Data Science, Operational Research, Computer Science, Informatics, Economics, or Engineering
• Excellent knowledge, experience and understanding of quantitative techniques (modelling, statistics, root-cause, etc.) applied to Risk Management with a focus on Card and Payments. Familiarity with key Risk and Performance Indicators. Experience working in one or more of the Card & Payments markets around the globe, with specific responsibilities in payments, retail banking, or retail merchant industries
• Good understanding of Payments and the Banking industry, including card verticals such as consumer credit, consumer debit, prepaid, small business, commercial and co-branded product
• Expert knowledge of data, market intelligence, business intelligence, and AI-driven tools and technologies, with demonstrated ability to incorporate new techniques to solve business problems
• Experience planning, organizing, and managing multiple large projects with diverse cross-functional teams, including resource planning and delivery implementation
• Experience in presenting ideas and analysis to stakeholders whilst tailoring data-driven results to various audience levels
• Develop Risk advisory related knowledge and capabilities creating next generation risk engagement with Visa clients
• Partner with in-market VCA consultants and data scientists to deliver risk-related advisory engagements
• Establish Intellectual Property (IP) risk repository for VCA by capitalizing on learnings from consulting engagements (e.g., build standard methods, create library of case studies, templatize modeling codes)
• Reengineer and/or package risk consulting methodologies and data driven solutions as appropriate, ensuring world-class best practices and efficiency through economies of scale
• Partner with other Visa functions (e.g., Risk, Products) to capitalize on existing risk products/solutions and co-design new ones leveraging Visa’s assets (expertise, data, capabilities)
• Proven ability to deliver results within committed scope, timeline and budget
• Very strong project management skills and experience
• Ability to travel within CEMEA on short notice
Technical Expertise
• Expertise in distributed computing environments / big data platforms (Hadoop, Elasticsearch, etc.) as well as common database systems and value stores (SQL, Hive, HBase, etc.)
• Strong understanding and experience of modern technology stack and microservice architecture including Kotlin, Spring boot, PostgreSQL, Kafka, AWS
• Relevant experience of engineering unstructured/structured data from Telco, Supermarket, Social Media, Online logs, E-commerce, etc is preferrable
• Ability to write scratch MapReduce jobs and fluency with Spark frameworks
• Familiarity with both common computing environments (e.g. Linux, Shell Scripting) and commonly-used IDE’s (Jupyter Notebooks), proficiency in SAS technologies and techniques is preferred
• Strong programming ability in different programming languages such as Python, R, Scala, Java, Matlab, C++, and SQL
• Experience in drafting solution architecture frameworks that rely on API’s and micro-services
• Familiarity with common data modeling approaches and ability to work with various datatypes including JSON, XML, etc.
• Ability to build data pipelines (e.g. ETL, data preparation, data aggregation and analysis) using tools such as NiFi, Sqoop, Ab Initio, familiarity with data lineage processes and schema management tools such as Avro
• Proficient in some or all of the following techniques: Linear & Logistic Regression, Decision Trees, Random Forests, K-Nearest Neighbors, Markov Chain Monte Carlo, Gibbs Sampling, Evolutionary Algorithms (e.g. Genetic Algorithms, Genetic Programming), Support Vector Machines, Neural Networks, Bagging and Boosting algorithms, etc.
• Expert knowledge of advanced data mining and statistical modeling techniques, including Predictive modeling (e.g., binomial and multinomial regression, ANOVA), Classification techniques (e.g., Clustering, Principal Component Analysis, factor analysis), Decision Tree techniques (e.g., CART, CHAID)