CCB-Risk-Fraud Machine Learning Data Science Modeler - Associate CCB-Risk-Fraud Machine Learning Data Science  …

J.P.Morgan
in New York, NY, United States
Permanent, Full time
Be the first to apply
Competitive
J.P.Morgan
in New York, NY, United States
Permanent, Full time
Be the first to apply
Competitive
CCB-Risk-Fraud Machine Learning Data Science Modeler - Associate
JPMorgan Chase & Co . (NYSE: JPM) is a leading global financial services firmwith operations worldwide. The firm is a leader in investment banking,financial services for consumers and small business, commercial banking,financial transaction processing, and asset management. A component of the DowJones Industrial Average, JPMorgan Chase & Co. serves millions of consumersin the United States and many of the world's most prominent corporate,institutional and government clients under its J.P. Morgan and Chase brands. Informationabout JPMorgan Chase & Co. is available at http://www.jpmorganchase.com/ .


Our Firmwide Risk Function is focused on cultivating a stronger,unified culture that embraces a sense of personal accountability for developingthe highest corporate standards in governance and controls across the firm.Business priorities are built around the need to strengthen and guard the firmfrom the many risks we face, financial rigor, risk discipline, fostering atransparent culture and doing the right thing in every situation. We areequally focused on nurturing talent, respecting the diverse experiences thatour team of Risk professionals bring and embracing an inclusive environment.
Chase Consumer & Community Banking (CCB) s erves consumers and small businesses with abroad range of financial services, including personal banking, small businessbanking and lending, mortgages, credit cards, payments, auto finance andinvestment advice. Consumer & Community Banking RiskManagement partners with each CCB sub-line of business to identify, assess,prioritize and remediate risk. Types of risk that occur in consumer businesses include fraud, reputation,operational, credit, market and regulatory, among others


The Machine Learning groupwithin the CCB Risk Fraud Modeling team is responsible for developing andimplementing best-in-class fraud prevention and detection models and analyticaltools. The team provides diverse modelsand analytical tools used to identify potentially fraudulent transactionsacross different lines of business (card, retail, auto, merchant services).

Working for one of the largest banks, card issuers, and paymentsprocessors in the US, you will be fighting crime and protecting consumers andsmall businesses from financial fraud, including account takeovers and identitytheft, with mathematical modeling. You will work in an industrialR&D/skunkworks environment, developing innovative predictive models on adataset in the hundreds of TBs.

In this role, you will be the analytical expert for identifyingand retooling suitable machine learning algorithms that can enhance the fraudrisk ranking of particular transactions and/or applications for new products.

Thisincludes a balance of feature engineering, feature selection, and developingand training machine learning algorithms using cutting edge technology toextract predictive models/patterns from data gathered for billions of transactions.

Your expertise and insights will help us effectively utilize big dataplatforms, data assets, and analytical capabilities to control fraud loss andimprove customer experience.

In addition, you will work with technologypartners to develop and improve cutting-edge real-time and batch modelexecution environments that process hundreds of millions of transactions perday.

  • Master's degree in Mathematics, Statistics, Economics, ComputerScience, Operations Research, Physics, and other related quantitative fields
  • At least 1 years' experience with data analysis in Python
  • Experience in designing models for a commercial purpose using some(at least 2) of the following techniques: CNN/RNN/other neural net, RandomForest/GBM/other tree ensemble, OpenCV/NLTK/GenSim/SpaCy/similar thematicpackages
  • A strong interest in how models work, the reasons why particular modelswork or not work on particular problems, and the practical aspects of how newmodels are designed


  • Preferred
  • PhD in a quantitative field with publications in top journals,preferably in machine learning
  • Comfortable working with bare-metal hardware in a Linux shell
  • Experience with model design in a big data environment via Hadoop,Spark and Hive
  • Experience designing models with Keras/TensorFlow, PyTorch, orother frameworks on GPU hardware
J.P.Morgan logo
Close
Loading...