Data Scientist - Senior

. Data Scientist - Senior page is loaded## Data Scientist - Senior remote type:
Remote locations:
Chicago, IL:
Scottsdale, AZ:
New York, NYtime type:
Full time posted on:
Posted 11 Days Agojob requisition :
JR101710

Established in 2021,
** Independence Pet Holdings
** is a corporate holding company that manages a diverse and broad portfolio of modern pet health brands and services, including insurance, pet education, lost recovery services, and more throughout North America. We believe pet insurance is more than a financial product and build solutions to simplify the pet parenting journey and help improve the well-being of pets. As a leading authority in the pet category, we operate with a full stack of resources, capital, and services to support pet parents.

Our multi-brand and omni-channel approach include our own insurance carrier, insurance brands and partner brands.
** Independence American Insurance Company (IAIC),
** a subsidiary of IPH, has over 50 years of underwriting experience and a history of innovation in the pet insurance industry. IAIC has built a reputation as a trusted and dependable partner. We are a pet-focused underwriter with deep insurance industry experience, offering a product with proven consumer appeal. Responsibilities
* Design and implement data pipelines for collecting, processing, and integrating structured and unstructured data from multiple sources, including internal databases and external data providers.
* Perform root cause analysis and utilize complex SQL queries to investigate data issues such as data inconsistencies, missing data, and errors.  Collaborate with data engineers, data analysts, and other stakeholders as needed.
* Ensure data accuracy and integrity by conducting data audits and creating reconciliation processes.
* Database management, including data cleansing, formatting, banding, pre-analysis and integration of data.
* Conduct exploratory data analysis to understand the relationship between data elements and insurance processes such as pricing, conversion, and retention.
* Develop rating plans using predictive models to optimize risk segmentation across a portfolio of products while balancing strengths and weaknesses of each model to the subject product.
* Use advanced statistical techniques to identify key drivers of sales and retention and create/maintain models to forecast expected results.
* Create and maintain dashboard visualizations in Power BI and Radar to monitor key metrics such as rate levels, risk segmentation, and retention.
* Collaborate with stakeholders across the company and communicate findings and recommendations to technical and non-technical audiences through reports, presentations, and visualizations.
* Stay abreast of industry trends, emerging technologies, and best practices in data science and actuarial science to drive continuous improvement and innovation.
* Establish best practices across the data science workflow, including but not limited to data preparation, modeling, and documentation.
* Serve as the data science subject matter expert and enrich predictive modeling knowledge and functional capabilities across the actuarial department.

Qualifications
* Bachelor’s degree in Data Science, Statistics, Mathematics, Actuarial Science, or a related field with relevant work experience.  Otherwise, Master’s degree or higher preferred.
* 5+ years of experience in a data science role, preferable in the insurance industry (P&C or A&H).
* Proficiency in programming languages such as Python, R, or SQL, with experience in data manipulation and statistical analysis.
* Experience with SQL Server and/or Snowflake/Databricks.  Familiarity with data warehousing concepts and tools.
* Experience with WTW’s Radar suite, including Radar Base and Emblem or Earnix.
* Experience using data visualization tools (Tableau, Power BI, or similar)
* Solid understanding of statistical techniques including GLMs, with the ability to build models and interpret results.
* Familiarity with a broad range of statistical techniques, such as regression modeling, Monte Carlo simulation, GLMs, mixed effects models, gradient boosting, random forests, neural networks, ensemble modeling…