Director of Data Analytics @ • Set the strategic vision for the four teams within Return Path’s Data Science and Analytics department. • Drive the strategy for Return Path’s Data Organization by working alongside senior leaders in engineering, product management and marketing as a core member of the Data Senior Leadership Team. • Oversee, manage and mentor 15 data scientists, statisticians and data analysts spread across the four teams in the department. • Provide the business context and framework for the teams within the Data Science and Analytics department to set and deliver on business-outcome oriented goals. From July 2015 to Present (4 months) Broomfield, COSr. Data Scientist & Manager of Data Feature Engineering @ • Defined and launched Return Path’s Feature Engineering team, which became a role model in the organization within its first quarter. • Managed, mentored and hired a team of data scientists that focused on the efficient development of scalable machine learning models. • Leveraged data from trillions of emails to build machine learning driven business solutions as Return Path’s lead data scientist. • Collaborated with Data Engineering to develop a process using Kafka, Storm and Thrift to deploy machine learning models that consume hundreds of millions of raw emails a day in real-time. • Routinely gathered, interpreted and scoped stakeholder requirements, developed the department’s first year-long rolling roadmap and participated in the Data Team’s quarterly agile planning as the acting product manager for the Feature Engineering team. • Led the department initiative to define measurable team-based KPIs and surface them to senior leaders in the company via dashboards. From January 2015 to July 2015 (7 months) Broomfield, COData Scientist @ • Led the technical components of a R&D project by working closely with clients and Executive team members to define and develop the Return Path’s first data-as-a-service product and third line of business, Consumer Insights. • Built a machine learning classification model with Python that efficiently categorizes hundreds of millions of purchased products into 50+ categories. • Created a PII redaction and re-identification risk process for a monthly data feed of tens of millions of rows. • Devolved prototypes of consumer loyalty metrics using unsupervised learning methods as part of a R&D project. • Designed and implemented an improved new hire on-boarding system and department wide career development program. • Mentored and trained a team of aspiring data scientists and statisticians. From April 2014 to January 2015 (10 months) Broomfield, COData Analyst @ • Developed a collection of predictive models in Python that efficiently classify the content of millions of email messages every day. • Created and automated the daily assignment of mailbox type categorizations to millions of email addresses using unsupervised clustering algorithms in R. • Built a predictive model and accompanying report that identifies our clients’ churn risk. • Designed and built multiple interactive data analysis web applications that have enabled internal staff to quickly and easily make better informed decisions. • Founded a predictive modeling challenge that teaches practical data science to staff across the company and provides crowdsourced solutions to valuable business problems. • Developed and taught weekly instructional sessions for colleagues on topics including: efficient programming in R and Python, machine learning, statistical analysis and project management. From January 2013 to April 2014 (1 year 4 months) Broomfield, COSenior Data Services Specialist @ • Managed all quantitative research services at NYU’s Data Services, including a team of 2.5 full-time staff members and 7 graduate student consultants. • Provided statistical computing assistance to faculty, staff and student researchers as the Data Service’s lead quantitative programming consultant. • Designed lessons, wrote training documentation and taught classes for statistical computing tools, including: R, High Performance Computing, SQL, SAS and SPSS. • Conceptualized, recommended and implemented integral revisions to the Data Service’s service model, including the support of High Performance Computing, SQL and Python. • Designed methods for the collection, analysis and reporting of internal usage metrics for the Data Services and High Performance Computing Clusters. From February 2012 to January 2013 (1 year) Data Services Specialist @ From January 2009 to February 2012 (3 years 2 months)

MS, Information Systems @ New York UniversityBA, Statistics @ Hunter College David McGarry is skilled in: Machine Learning, Python, Team Leadership, Mentoring, Natural Language..., Predictive Modeling, Unsupervised Learning, R, Statistics, Data Mining, Dimensionality Reduction, Feature Selection, Hive, SQL, Bash