- Currently leading the development of a reactivation model aimed at recruiting lapsed customers, utilizing predictive analytics to drive engagement and improve customer retention, contributing to overall business growth.- Led analytics initiatives to identify key cancellation trends, enabling the development of targeted strategies that optimize the customer journey and reduce post-shipment cancellations, significantly reducing return-related costs and enhancing operational efficiency.- Scoped and implemented an RFM (Recency, Frequency, Monetary Value) model to rank and identify customers thereby increasing the monthly conversion rate.- Analyzed product line effectiveness and inter-dependencies to inform customer acquisition and retention strategies across multiple marketing channels.- Developed an automated financial dashboard using Power BI to improve pricing forecasts and increase overall financial strategy effectiveness. - Significantly contributed to the group’s success by developing and maintaining comprehensive documentation for major projects within the data team, ensuring clarity and consistency.[Python, SQL, PowerBI]

Spent time with family and worked on personal development

-Developed algorithm for identifying highly prospective customers and top small business owner leads-Improved and maintained Next Best Offer algorithm for cross‑selling to current MM customers- Improved and maintained up‑selling pipeline for existing customers, leveraging customer data to identify additional sales opportunities- Collaborated with cross‑functional teams to maintain and optimize an attribution pipeline, implementing data‑driven attribution models toanalyze the lead impact and use insights gained to inform and optimize lead generation strategies- Conducted customer attrition analysis for investment products, identifying key factors driving churn and developing retention strategies- Led migration of legacy leads generation pipeline to a new platform, ensuring seamless integration and minimal disruption to operations- Supported software engineering team with backend microservice development for an internal leads delivery tool

Marketing:- Developed predictive models for the identification of highly prospective MM customers (leads).- Curated data to additionally identify top business owner leads to sell MM products.- Supported software engineering team with backend microservice development for an internal leads delivery tool. [R, Python, SQL, Pyspark, Docker, Kubernetes, Kafka]Risk and Product Domain:- Made key contributions to the development of algorithmic underwriting models for Disability Insurance- Worked on model output explainability using an internal Shapley tool- Conducted research and testing of data imputation methods for continuous improvement of current underwriting tool- Performed ad-hoc comparative analyses of data vendors and their effectiveness. [R, Python, SQL, Jenkins]Volunteer Champion:- Collaborated with Engineers and Analysts to build a web calculator (Cliff‑Effect Calculator)that quantifies the loss of government support thata person bears when there is a monetary change in his/her take‑home income- Worked as a liaison between industry professionals and local educational institutions in Hampshire County (MA) to support and facilitate work‑shops at inter‑collegiate Hackathons and Datafests- Supervised and mentored Junior Data Scientists in their academia‑to‑industry transition

- Worked on determining the effectiveness of the NSF I-Corps program by analyzing survey data to identify entrepreneurial trends and spinoff potential among prospective academic research projects.- Responsible for streamlining data management procedures within the organization.- Processed structured and unstructured datasets for statistical analysis and public release of the data [R]

- Developed a supplementary model for integration into the organization’s internal predictive goods pricing tool.- Built an XGBoost model to perform damaged goods classification on big data (over 25 million entries).[Python, MSSQL]

- Developed a decision support system to predict merchants going out of business using Time Series analysis - Performed feature engineering, data wrangling, and data mining operations on large datasets with over 0.5 million entries [Python, SQL]