Sheenu Abraham

** ****** **** **, ********** SC *9607 614-***-**** adztwc@r.postjobfree.com

SUMMARY

With 16 years of experience as an analytics professional, I have provided advanced analytical solutions using Machine Learning algorithms across various industries. My skills include Machine Learning, Statistical Analyses, R, Python, SAS, and proficiency in data science working platforms such as Jupyter, Spark, and Databricks. I am experienced in working with Agile methodologies such as Scrum and Kanban, using tools like GitHub, Confluence, and Jira for project management, collaboration, and tracking. Adept at working individually and in cross-functional teams, I have excellent communication skills to convey complex reports and analyses to clients and stakeholders. EXPERIENCE

Target RWE, Durham NC

Principal Data Scientist (Oct 2022 – present)

● Built out tools and capabilities to improve the effectiveness and usability of the internal self-service data hub.

● Developed and productionized an NLP solution with two-way encryption that identifies and redacts PII entities as well as identifying clinical entities from raw medical record/clinical notes, resulting in a more robust data ingestion pipeline.

● Provided scientific and analytic input to protocol, developed statistical analysis plan, and participated in drafting of manuscripts and external disclosures.

● Applied advanced analytic methods to data based on understanding of the healthcare system to deliver real- world evidence and interpret results to better enable drug development teams.

● Evaluated John Snow Lab healthcare models to implement in the current data pipeline. Senior Data Scientist (Sep 2021 – Sep 2022)

● Transformed real-world data sources (related to patient journeys and treatments) to analysis-ready data sets enabling rapid generation of evidence.

● Developed and deployed a Flask application as a service on the internal self-service data hub that enables users to upload files and generate Tableone summary statistics customized to the user’s requirements.

● Built NLP solutions for eligibility screening and recruitment for the study of advanced therapies.

● Provided scientific and analytic input to protocol, developed statistical analysis plan, and participated in drafting of manuscripts and external disclosures.

Red Ventures, Charlotte NC

Data Scientist II (Oct 2019 - Aug 2021)

● Led the development and deployment of a of an affinity model that utilizes customer behavior attributes to predict propensity to convert and utilize the propensity scores to segment audiences for effective remarketing campaigns.

● Led the development and deployment of a production level Analytics dashboard in Shiny that forecasts expected leads from partners in the Higher Ed vertical.

● Implemented Linear Optimization to derive maximum revenue as well as maintain the optimal school mix for the overall school portfolio.

● Developed and deployed a bid predicting model (in Scala) and deployed in Databricks for ads displayed in the Snapchat app.

● Led the development of the Search Query Mining tool that assists SEO Analysts to gain insights in a timely manner. This included the implementation of NLP techniques for keyword extraction from search queries with RAKE analysis.

SCOR Global Life Research & Development, Charlotte NC Data Scientist (March 2016 – Sep 2019)

● Develop advanced statistical, predictive, and machine learning models that reflect or augment actuarial models.

● Research and evaluate current and emerging underwriting data and risk assessment algorithms such as LexisNexis’ Risk Classifier and TransUnion’s True Risk. Develop a set of actionable parameters for nontraditional underwriting factors and support the creation of business models that supplement or replace traditional underwriting requirements.

● Partner with internal customers to replace automated underwriting processes with predictive models.

● Developed a model that predicts lapse rates & mortality utilizing policyholder characteristics and post-level term structure, thus replacing static tables with a dynamic lapse function. Authored article with findings.

● Built multiple predictive models to replace the current Lapse Assumption with a more robust, data-driven alternative for various products across the blocks of business.

● Developed an ARIMA Model that forecasts expected paid claims based on historical data. Atrium Health, Charlotte NC

Senior Statistician (Sep 2014 – Feb 2016)

● Implement the automation of SAS ETL processes that extracts data from multiple data sources, manipulates, merges, and loads integrated data into REDCap (Research Electronic Data Capture) databases using the API functionality.

● Automated the legacy process of STAR (Billing) datasets using SAS EG for Atrium Regional and Non- Regional Facilities that are used for Data Quality Measures and Reporting. Health Management Systems, Columbus OH

Statistician (Mar 2008 – Aug 2014)

● Conduct statistical analysis on healthcare databases (Medicaid and managed-care organizations) using SAS, descriptive statistics, hypothesis testing, linear and logistic regression and sample size calculation.

● Performs statistical sampling and quality checks of sampling methods and analyzes data and pertinent facts to prepare clear and concise analytical reports.

Abigail Wexner Research Institute, Columbus OH

Biostatistician (Jul 2007 – Feb 2008)

● Develop and use statistical models and data analysis programs to help with ground-breaking simulation studies of various statistical approaches to genetics, within the field of pediatric illnesses and disorders. Health Management Systems, Columbus OH

Health Research Analyst Intern (2006 – 2007)

The Ohio State University – Colleges of Arts and Sciences, Columbus OH Assessment Coordinator Graduate Assistant (2005 – 2007) EDUCATION

The Ohio State University, Columbus, OH

Master of Applied Statistics (2007)

University of Kerala, India

Bachelor of Engineering in Computer Science and Engineering (2002)

Contact this candidate