Data Scientist / Lead Data Scientist

  • 34289
  • Non-Life - Data Science
  • |
  • Ohio, United States
  • |
  • Sep 25, 2018
Insurance
RESPONSIBILITIES
  • Making sense of diverse datasets related to key business problems.
  • Responsible for the full stack of data analytics, including querying or otherwise procuring data, cleaning data, feature generation, problem formulation, error / success metric choice, machine learning / predictive model building, and translation of results into business action.
  • The final product can range from reporting that will be used to advise strategic planning, to recommendation of a specific action, to handing off a predictive model for deployment in production.
  • Responsible for solving a wide variety of problems, including our core business problem of understanding how mobile sensor data can measure driving behaviors and risk.
  • Advertising more cost-effectively, making all our various teams and processes more efficient, and pricing our products more accurately.
  • Mining raw text data for use in classification / predicting business outcomes.
  • Topic classification based on raw audio recordings.
  • Building models to detect fraudulent customer activity.
  • Applying machine learning to image classification for key business applications.
  • Identifying, evaluating, and productionizing new data sources.
  • Predictive modeling related to estimating the final cost of an open claim.
QUALIFICATIONS
  • Master’s degree or Ph.D. in mathematics, physical sciences, or engineering.
  • 2+ years’ experience building predictive models in a business setting.
  • Advanced R or Python.
  • Demonstrated experience in building, validating, and leveraging machine learning models.
  • Demonstrated experience with image classification and/or natural language processing.
  • Demonstrated skill with data mining, data munging, coping with missing / corrupt / unstructured data.
  • Deep understanding of key probability and statistics concepts.
  • Ability to identify and learn new tools and techniques as needed.
  • Passion for empirical research and answering difficult questions with data.
  • Strong problem solving skills, attention to detail and solid collaboration skills.
  • The ability to take an ambiguous business problem and translate it into a well-posed mathematical problem.
  • Preferred Skills:
  • Experience using big data tools.
  • Experience with anomaly detection methods.
  • Advanced physics knowledge.
  • Advanced linear algebra knowledge.
  • Experience with version control.
  • Experience building insurance pricing models.
  • Experience with design of experiments.