Data Scientist at CNA
Headquartered in the heart of downtown Chicago, CNA is a leading commercial and specialty insurer, offering a diverse range of insurance products including Workers Compensation, Property, General Liability, Professional Liability, Cyber Insurance, Surety, and Warranty. We are one of the world leaders in underwriting non-medical professionals, from lawyers and accountants to architects and management consultants.
What CNA offers
• A collaborative data science team with diverse skills and experiences, combined with deep expertise in statistical modeling, machine learning, and applications to insurance
• Modern cloud computing environment that enables you to explore data, build and deploy sophisticated models that impact key areas such as underwriting, pricing, claims management and risk control
• Sponsorship of continued professional growth through support for attending technical conferences, meetings and symposia
What we are looking for
The successful candidate will:
• Use statistical methodologies and machine learning techniques to build state-of-the-art predictive models for the pricing, underwriting, claims, operations and marketing for an exciting mix of business insurance products
• Translate business problems into innovative analytical solutions
Essential Duties & Responsibilities
• Builds predictive, prescriptive or descriptive models in collaboration with business partners in functional areas such as Underwriting, Pricing, Distribution, Claims, Risk Control and IT to help address business questions.
• Designs, writes, and tests advanced computer programs to extract, visualize and analyze data, to build models and to support model deployment into production.
• Interprets the results of models in business terms and communicates the contents of the models to business decision-makers .
• Participates in crafting products and innovative solutions that will provide revolutionary change.
• Participates in special projects requiring advanced quantitative expertise.
Required Skills, Knowledge & Abilities
• Experience in merging, cleaning, and preparing data for analysis from multiple sources
• Experience in extracting meaningful information from data using visualization and by formulating and testing hypotheses.
• Proficiency with SQL and programming experience in R or Python
• Proficiency with classical Generalized Linear Models, statistical inference, and re-sampling methods.
• Proficiency in Linux
• Practical experience with version control (git, SVN)
• Strong analytical, problem solving and critical thinking skills
• Attention to detail and accuracy of work, ability to spot and correct issues
• Strong interpersonal and communication skills
• Strong writing skills, including writing coherent documentation and reports
• Drive to continuously improve and learn new tools and methods
• Ability to work collaboratively with colleagues with diverse perspectives and backgrounds
• Strong time management skills
• Capable of operating with little supervision and thinking independently and innovatively
Preferred Skills, Knowledge & Abilities
• Practical experience with distributed computing (e.g., Apache Spark)
• Experience developing packages in R or Python
• Experience with natural language processing
• Knowledge of insurance
• Experience in building machine learning models
AVP or above
Education & Experience
Advanced degree in a quantitative discipline, with relevant work experience preferred.