Data Scientist - Payment Systems Risk
- Full-time
- Job Family Group: Product Development
Company Description
At Visa, your individuality fits right in. Working here gives you an opportunity to impact the world, invest in your career growth, and be part of an inclusive and diverse workplace. We are a global team of disruptors, trailblazers, innovators and risk-takers who are helping drive economic growth in even the most remote parts of the world, creatively moving the industry forward, and doing meaningful work that brings financial literacy and digital commerce to millions of unbanked and underserved consumers.
You're an Individual. We're the team for you. Together, let's transform the way the world pays.
Job Description
The Payment Systems Risk team within Visa Data Product is responsible for building critical risk and fraud prevention applications and services at VISA. This includes idea generation, architecture, design, development, and testing of products, applications, and services that provide Visa clients with solutions to detect, prevent, and mitigate risk for Visa and Visa client payment systems.
The team closely collaborates with other analytic stakeholders to understand the business problem in order to determine the most appropriate analytic approach that provides meaningful results to customers. Responsibilities include delivering projects on time and within scope with an in-depth knowledge of big data and cutting edge data mining techniques as well as the use of predictive, classification, machine learning and alternate analytic algorithms for modeling and segmentation.
Essential Functions
- Execute model implantation and performance tracking for risk models; generate performance analysis at the aggregate level, as well as issuer level. Interpret and present performance results to non-technical audience.
- Compile complex predictive model packages for production deployment; support model installations, and monitor and calibrate production models.
- Propel analytic product development via conducting statistical analyses on various data sources; and add values to products by being innovative and applying the analysis.
- Assist in scoping and designing financial and analytic metrics to measure development and production outcomes and produce performance reports.
- Find opportunities to create and automate repeatable analyses or build self-service tools for business users.
- Conduct transaction data analyses with Hadoop/Cloud and big data technologies for internal and external product owners, and develop deeper insights into the products using advanced statistical methods.
- Work on cross functional teams and collaborate with internal and external stakeholders.
- Promote big data innovations and analytic education throughout the Visa organization.
Qualifications
Basic Qualifications
- 2 years of work experience with a Bachelor’s Degree or at least 0 years of work experience with an Advanced degree (e.g. Masters, MBA, JD, MD).
Preferred Qualifications
- Minimum of 1 year of experience in developing statistical predictive models.
- Real world experience using Hadoop and the related query engines (Hive / SparkSQL).
- High level of competence in Python, Spark and Unix/Linux scripts
- Experience with SAS/SQL/Hive for extracting and aggregating data
- Ability to program in one or more scripting languages such as Perl or Python and one or more programming languages such as Java or Scala
- Experience with one or more common statistical tools such SAS, R, KNIME, Matlab.
- Proficiency in designing & solving classification/prediction problems using open source libraries such as Scikit learn.
- Deep learning experience with TensorFlow is a plus.
- Proficiency in data manipulation using Python tools such as Pandas, Numpy etc.
- Experience with data visualization and business intelligence tools like Tableau is a plus.
- Modeling experience in bankcard industry or financial service company using for fraud, credit risk, bankruptcy, or marketing is a plus.
Additional Information
Visa will consider for employment qualified applicants with criminal histories in a manner consistent with EEOC guidelines and applicable local law.