Senior Data Scientist
CurrentKey Achievements• Drove ideation, design, development and deployment of an online Entity Resolution system providing visibility into $1.2B+ in disparate customer revenue across 13M accounts through business logic, NLP, Similarity Search via LLM, and graph analytics• Ranked 50M customers via classification/regression to identify 360k marketing targets worth $1.02B in expected revenue• Classified the churn risk of 710k customers with 93% Recall and revenue impact of $46.2M to advise outreach• Determined drivers of customer satisfaction by analyzing 3k surveys using NLP, clustering, regression to inform call center reps• Applied Interrupted Time Series method to customer revenue forecasting to account for $282M Covid-19 revenue impact• Used quasi-experimental Synthetic Control Method to measure ~$400M in annual benefit from exclusive service offerings• Implemented Change Point Detection model to help the client capitalize on early recognition of sector revenue trends• Segmented customers into tiers via clustering in effort to provide levels of service that prevent churn and encourage spend• Engineered 80+ data features for lead generation and ranking models through complex SQL/SAS queries• Piloted Informatica Enterprise Data Catalog tool to develop 100+ data assets, connecting 7 data silos• Integrated 26 tables across 5 HR vendor systems to help improve visibility for candidates and reduce time-to-hire by 30%Additional Responsibilities• Grew account billings by $1.1M+ through sale of new solutions by developing client relations and proving technical capabilities• Presented analytics solutions/insights to clients and handled technical inquiries as lead data scientist and architect• Hired and mentored junior data scientists, multiplying team’s impact by broadening scope and growing depth of solutions• Led team by architecting solutions, improving internal processes, removing blockers, and encouraging training opportunities