Data Scientist II

Job description

General Summary

Elevate is a globally distributed technology firm which develops next-generation financial products focused on managing life’s everyday expenses. The Data Science team conceptualizes, develops, deploys, and maintains predictive models using advanced statistical and machine learning methods. These models are used in Elevate’s Underwriting, Account Management, and Operations applications. Additional responsibilities include developing and implementation of complex analysis to drive business decisions for our organization. The Data Scientist II will have a higher focus on technical ability and out of the box thinking.

Principal Duties And Responsibilities

  • Design, Develop and Deploy advanced machine learning models for use in Underwriting, Customer Management, Marketing, and Operations;
  • Assess, clean, merge, and analyze large datasets adhering to standardized data manipulation techniques and methodology by leveraging R, Python and/or Apache Spark;
  • Perform efficient parallel processing computations both within R as well as cluster computing technologies such as Apache Spark.
  • Proficiency in multiple linear and nonlinear algorithms for testing, development and deployment into our underwriting engine in the application of risk management in all of Elevate’s acquisition channels;
  • Efficiently apply data mining methodologies to minimize credit/fraud losses, maximize response and approval rates, and develop methods to enhance profitability of Elevate products;
  • Assist in the implementation of scoring models on multiple decision platforms Including R instance deployment, On premise deployment and cloud deployment and multiple forms such as Java objects, R Object Models and Apache Spark Models;
  • Provide knowledge and insight on the third party data providers such as Transunion, Clarity/Experian and Equifax to include knowledge of products and data available, effective use of variables, data dictionaries as well as advantages and limitations;
  • Maintain clear, detailed model documentation on our Wiki Server by leveraging reproducible research technologies such as Rmarkdown, IPython, Jupyter Notebook, etc.;
  • Interact with business partners to support the needs and goals of all Elevate portfolios, Rock teams, Braintrusts and Pods.

Experience And Education

  • Minimum M.S./M.A. in a highly quantitative field (Computer Science, Statistics, Economics, Mathematics, Business or other quantitatively oriented degree) required. Doctoral Degree is a plus.
  • At least two years of experience in Data Science, Risk or Modeling for consumer lending; Professional experience waived with Ph.D. Degree in highly quantitative field
  • Demonstrated proficiency with advanced statistical modeling and substantial experience with machine learning techniques (e.g., Random Forest, Gradient Boosting, LASSO, Elastic Net, etc.). Knowledge of penalized regression and classification methods a plus;
  • Solid experience in analyzing, recommending and implementing Risk strategies
  • Proficiency of at least two Advanced Statistical Analysis Tools such as R, Python, Scala, Java, SAS, MATLAB, SQL, STATA and/or SPSS; knowledge with versioning software (e.g., Git), big data solutions and data processing frameworks (e.g., Spark, Hadoop);
  • Experience with at least four database technologies such as Access, MSSQL Server, SAS Datasets, Hadoop, Apache Hive/Impala, Spark, Redshift, HBASE, Kafka, Spark Streaming, Neo4j, Teradata, Oracle, MySQL, DB2, Amazon AWS, Cassandra, PostgreSQL, NoSQL, JSON & XML parsing, etc.
  • Experience working in fast-paced environment with ever-changing demands
  • Good communication skills for communication with Risk Management peers
  • Experience in financial services and/or Credit Risk Management or target marketing preferred
  • Knowledge of contemporary supervised and unsupervised data mining techniques a plus

Please let the company know that you found this position on this Job Board as a way to support us, so we can keep posting cool jobs.