While working as a Lead Data Scientist at Verisk, I've connected several key datasets together within the Personal Lines Auto space. I function as the business consultant and SME for a newly acquired dataset, leading to multiple new products and projects. In addition, I have created several new data pipelines utilizing the Databricks platform. ACHIEVEMENTS/RESPONSIBILITIES- Established new product offering by planning and joining two databases with over 3 billion total records using Databricks platform- Created data pipeline to combine and categorize nearly 30 different datasets with over 75 million total rows- Engineered 50+ features from four separate data streams containing over 2000 fields to stage data for machine learning- Functioned as business consultant and SME for dataset with more than 20 billion data points that generates $10M+ revenue annually- Executed market research in coordination with product and marketing teams to drive customer conversations and internal decision-making

Data Driven Safety is a public data aggregator in Huntersville, NC aimed at using public data for public good. In my time as Director of Analytics at DDS, I engineered several high-importance projects including developing and launching an automated quality assurance system. In addition, I assessed complex data quality issues and coordinated all data testing and transfer with new and existing clients. ACHIEVEMENTS/RESPONSIBILITIES- Designed and launched automated quality assurance system resulting in a 100% efficiency increase in QA department- Spearheaded development of client-facing web service including MySQL query optimization, algorithm selection, and performance testing resulting in 50% decrease in average response time for clients - Assessed complex data quality issues with Python and Bash scripting knowledge leading to savings of $80,000 annually- Handled data testing and transfer for all new business opportunities resulting in a 15% increase in revenue- Coordinated with existing clients to ensure completion of 10 to 15 requests weekly

As a Data Analyst for Data Driven Safety, I oversaw 400+ datasets accounting for ~60% of company revenue. While in this role, I utilized my self-taught Python knowledge to solve outstanding data quality issues. I also assisted in MySQL query development and execution. ACHIEVEMENTS/RESPONSIBILITIES- Leveraged self-taught Python skills to eliminate 20% of outstanding high-importance bugs- Composed over 100 MySQL database update queries and confirmed their success across three production databases, freeing 15% of lead developer time- Identified and rectified over 1000 data quality issues while overseeing key datasets accounting for 60% of company revenue- Developed canned MySQL queries to check format of 50 to 100 important data fields, reducing development time by nearly 75% and becoming the standard for quality testing

- Performed a comprehensive analysis of the underwriting process to determine inefficiencies, and reported the results back to the company- Charted over 1400 data points and evaluated them in order to improve employee efficiency- Acted as the liaison of communication between process analysts and underwriting personnel.

- Organized and managed data related to women and millennials in the workforce to enhance opportunities for these groups in the organization.- Unearthed a key insight that is now driving change within the company.- Performed extensive research on the HR Analytics space including competitor data analysis and presented back to the business.