Post Job Free

Resume

Sign in

Data Science Scientist

Location:
Yonkers, NY
Posted:
September 28, 2023

Contact this candidate

Resume:

Abigail Charles

718-***-**** adz0ya@r.postjobfree.com

DATA SCIENCE DIRECTOR

Meticulous Data Science Director with extensive experience in interpreting a wide variety of technical instructions in mathematical and or statistical form, with several abstract and concrete variables. Proven history of budling and implementing data science strategies across business units. A strong leader and people manager with excellent communication and coding skills.

TECHNICAL SKILLS

Tools (Modeling, ETL, BI): SAS SPSS R STATA Python Hadoop Ecosystem: Hive Pig Flume Drill Spark

Data Pipelines - Spark Streaming Spark SQL MLlib GraphX Certified Spark Developer H2O-3 Open Source

H2O Driverless AI H2O-Q

Programming: SQL SAS R Python

ML/Statistics: Survival Analysis Regression - Logistic / Ridge / Linear Bayesian Analysis GBM Xgboost Linear Programming NLP Time Series A/B Testing Hierarchical Models Sampling Methodology and Experimentation Biostatistical Methods Survival Analysis

Clinical Trials: ICH guidelines GCP SOP Phase 1-4 Oncology Statistical applications to clinical trials RWE/RWD

PROFESSIONAL HISTORY

CVS Pharmacy March 2022-Present

Lead Director of Rx Retail Pharmacy

Hired and developed a team of 15 data scientists to target the wider Rx Retail Pharmacy growth goals through advanced analytics, ML and experimentation.

Generated $30M in Revenue 2022-2023.

Lead a team of 15 data scientists, including Sr. Managers, Lead and Sr. Data Scientists. The team was divided into 3 sub-teams: Experimentation, Modeling and Growth, Clinical Studies

Built the roadmap and strategic goals for the data science team to align with the business Retail Pharmacy team.

Lead a portfolio of multiple workstreams focused on developing and delivering patient adherence analytics and ML solutions to CVS leadership.

Partnered closely with the Rx Pharmacy Growth and Clinical teams to build and measure multiple experiments to evaluate the efficacy of adherence programs.

Partnered with the Omnichannel business team to develop models and experiments to target better patient outreach experience.

Work closely with VPs and SVPs in Digital, Retail Pharmacy, and Data Engineering to inform business strategy and identify new business opportunities.

Developed analytics to target VP goals for reducing adherence disparities within the Health Equity team.

Communicate with executives to relay adherence performance metrics and program impact assessment.

Orum.io (payments platform) October 2020-March 2022

Lead Data Scientist

Developed the strategic direction for DS needs to enhance product capabilities based on customer feedback and user experience in the payments/money movement space.

Generated $10M in Revenue 2020-2022.

Identified and monitored key business risks and realized the data needs of the business.

Managed and lead the junior data scientists (10), as well as oversaw all activities ensuring alignment with departmental and business-wide vision and strategies.

Played a mentorship role to key data science positions, guiding them through the execution of their duties, and encouraging their professional growth in preparation for the next steps of their careers.

Played a strategic role in continuously improving the business’s data analysis model, creating industry-leading performance through the leveraging of new and creative data-sources, and employing the latest in machine learning in the department.

Collaborated and worked closely with other Data and Analytics Teams, inclusive of data analytics, data warehousing, and data engineering teams in creating applications through the utilization of structured and unstructured data, designing optimal data architecture, and experimenting on new machine learning techniques.

Abigail Charles adz0ya@r.postjobfree.com Page 2

H2O.ai September 2019-July 2020

Lead Data Scientist

Lead data science team in presenting to customers H2O capabilities.

Generated $3M in Sales 2019-2020.

Performed scoping of use cases to include machine learning solutions for customers across healthcare, manufacturing, pharmaceuticals and telecom.

Trained in H2O products (open source and closed source) internally and externally.

Developed machine learning products.

Involved in strategic direction for product growth based on customer feedback and user experience.

Mckinsey & Company July 2018-September 2019

Expert (Director level), Data Scientist

Led teams of data scientists and data engineers across healthcare client facing teams (20-25).

Played pivotal role in deep dive problem solving sessions to create the most impactful models and model results for client problems.

Led workshops with clients across multi-disciplinary teams to identify and bridge business opportunities with data science solutions.

Collaborated with Mckinsey’s strategy and analytics teams to glean and present polished insights from analyses.

Contributed substantially to developing and expanding the healthcare Data Science COE advanced analytics capabilities, knowledge and expertise.

PwC January 2017-December 2017

Led teams of data scientists and data engineers across healthcare client facing teams (20-25).

Data Science Manager

PwC Client 1: Baker Hughes

Build out an analysis plan for predictive models to detect failure of parts of a drilling tool, and drive the adjustment of thresholds (temperature setting, vibrations settings etc.) which signal that a part needs to be replaced.

Managed a team, selected the correct predictive models and wrote the code to achieve outputs as directed by the analysis plan.

Ensured the delivery of a product that met the client’s needs. Generated $5M in savings 2017.

PwC Client 2: Blue Cross Blue Shield North Carolina

Data Science Manager

Integral to the scope development for analyzing what effect the client’s current programs are having on their Star Quality ratings.

Constructed the analysis plan to meet scope needs.

Managed a team that ran the analytics and compiled client deliverables as each milestone the analysis plan was met.

PwC Client 3: IPL (Indiana Power and Light)

Data Science Manager

Provided insight and guidance on newer machine learning techniques to solve problems for predicting meter fires and unbilled revenue.

PwC Client 4: Mayo Clinic

Data Science Manager

Provided statistical guidance for development of R Shiny and R Markdown applications depicting survival curves, forest plots and accompanying descriptive statistics for cancer patients on specific drug cohorts.

Testing and implementing machine learning techniques (random forest, market basket analysis etc.) to find out what drug a patient should use once their current drug regiment has become ineffective.

Clarity Solution Group November 2015-December 2016

Senior Consultant, Data Scientist

Understood requirements of client and worked with big data (e.g., parallel/MapReduce algorithms).

Created statistical models which allowed client to make more informed business decisions.

Abigail Charles adz0ya@r.postjobfree.com Page 3

Hands-on utilization of tools like SAS, SPSS, and R.

Collaborated with both strategy and full lifecycle implementations for nationally based clients.

Demonstrated proficiency in predictive analytics and data mining.

Implemented data warehouse solutions.

Clarity Solution Group Client 1: CareSource

Fraud Detection Analytics

Senior Consultant-Lead Data Scientist

Developed three strategic use cases for the client to target potential fraudulent providers.

Implemented SAS EG based platform that capable of running the fraud detection analytics both prospectively and retrospectively.

Set the platform for predicative modeling to build out a robust and client-specific fraud detection engine.

New EDW (Enterprise Data Warehouse) Requirement Development

Senior Consultant-Senior Data Analyst

Analyzed all existing datasets available in SAS format to create an inventory of all table names, columns, sizes and other significant attributes that was necessary to document before transition to the new EDW.

Used information collected from interviews with analysts throughout the firm to create detailed business and technical requirements needed for the implementation of the new EDW.

Clarity Solution Group Client 2: Blue Cross Blue Shield of Kansas, Topeka

Senior Consultant-Data Scientist

Involved in the development of three use cases targeting membership retention, product viability and an online/phone member satisfaction survey.

Implemented text mining methods in R (dendrograms, word clouds, hierarchical clustering) to analyze online survey of member satisfaction.

Implemented multivariate data analysis in R (robust linear regression and decision trees) to build predictive models to identify:

Where members who are “On Exchange” (selling of health insurance products to individuals online) would move once old insurance products are eliminated and new ones are added.

To predict the riskiness of new members joining and the types of insurance products that they are attracted to purchasing.

Used Tableau to visualize both product and member segmentation aspects of the more complexed modeling listed above.

United Health Group (UHG), Optum December 2012-December 2015

Senior Data Scientist-Advanced Analytics Lab

Developed modules and enhanced methodology pertinent to the choice of study design and analysis of medical claims data in order to meet the needs of customers, which included building and updating models and rules to identify aberrant medical claims billing in the ‘CHALLENGER’ fraud detection engine.

Used advanced statistical techniques in SAS such as applications on sampling, forecasting, predicting and estimating for non-CHALLENGER and CHALLENGER adjacent projects.

Generated savings $20M in savings 2012-2015.

Implemented dual model for reducing false positive rates within CHALLENGER and developing rules for tagging the abuse of ‘Multi Facet Injection Per Visit’ A total of $15M annually was recouped by the company as result of the implementation of all modules worked on.

Developed and implemented integration of VBA and SAS macros to automate routine analyses for prospective fraud activities.

Architected algorithms into a unique tracking system in Access DB for analysts work progress with the Advanced Analytic Lab.

Presented findings of studies to SMEs and upper management, also trained and mentored staff.

Life cycle development of ETL processes for data migration of the OPTUM Payment Integrity System AAL team data into the new PAWS.

Abigail Charles adz0ya@r.postjobfree.com Page 4

Managed fPSM (Facility Predictive Scoring Model) within predictive analytics. A total of $5m year to date in savings have resulted.

Healthfirst, Finance Corporation October 2011-December 2012

Senior Data Analyst

Advanced SAS programming for automation Finance Corporate/Finance Analysis processes including IBNR allocation.

Developed and implemented GUI in Access, which utilized VBA and SAS programming languages to facilitate accountants with IBNR allocation calculation.

Performed Ad Hoc SAS programming needs to facilitate Finance Corporate activities.

UAT approval and sign off.

Designed queries to identify and analyze data across multiple data sources and creates reports for Healthfirst lines of business: SHP, CHP, MEDICARE, MEDICARE, MHICOMM, NJCARE, and NJCAID.

Delivery of informatics and adhering to regulatory and departmental data integrity standards and requirements to support contractual obligations with the NYSDOH, CDOH, LDSS, and CMS.

Maintained reference tables for mapping data warehouse tables in SAS.

Microsoft Dynamics AX System Administrator: Created comprehensive manual that documented how Health first’s data warehouse interfaced with AX; troubleshot errors related to dimensional sets, focuses and hierarchies.

College of Physicians & Surgeons (Oncology), Columbia University December 2010-September 2011

Biostatistician

Analyzed data from clinical trials using SAS, STATA and SPSS. Methods for analysis include, time series analysis, survival analysis, regression (OLS, GLM) and generalized estimating equations (GEE). Managed junior staff.

Designed small pilot studies to estimate statistical parameters for future studies. The three large datasets frequently used are:

Premier’s Perspective Rx-the US’s largest hospital drug utilization and financial database. It includes more than 500 acute care facilities and approximately 80 million patient records.

Nationwide Inpatient Sample (NIS)-the US’s largest longitudinal all-payer inpatient care database. It is also the only national hospital database containing charge information on all patients, i.e., persons covered by Medicaid, private insurance and uninsured.

National Cancer Institute Surveillance, Epidemiology and End Result Program (NCI-SEER)-collector of information on cancer incidence, survival and prevalence from specific geographic areas representing 26% of the US population.

Produced statistical analyses reflecting the outcome from clinical trials which followed the efficacy of robotic vs laparoscopic hysterectomy surgeries.

ADDITIONAL RELEVANT EXPERIENCE

Mailman School of Public Health, University of Columbia

Associate Fellow

College of Dental Medicine, Columbia University

Statistician, Research Coordinator

Mailman School of Public Health, Columbia University

Research Assistant

NYC Department of Finance, Tax Policy Office

SAS Programmer, Data Analyst

World Bank

Consultant

Abigail Charles adz0ya@r.postjobfree.com Page 5

EDUCATION

Doctor of Philosophy in Mathematics and Education

Research Field: Mathematical/Statistical Applications and Genetics.

Dissertation Title: Statistics for Learning Genetics

Columbia University

Master of Philosophy in Mathematics and Education

Columbia University

Master of Public Administration in Advanced Economic and Policy Analysis

Columbia University

Master of Arts in Applied Statistics

Columbia University

Bachelor of Arts in Economics and Mathematics

St. Joseph’s College

CERTIFICATIONS PROFESSIONAL DEVELOPMENT

Training in Hadoop Ecosystem: Hive, Pig, Flume, Drill.

Training in Spark: Build and Monitor Spark Applications; Create Data Pipelines (Spark Streaming, Spark SQL, MLlib, GraphX)

Certification in SPSS Training through the World Bank and OECS (Organization of Eastern Caribbean States) Secretariat.

Training in the use of STATA, Rand SAS.

VBA (Visual Basic for applications) and SQL programmer with specialization in Excel spread sheets and Access databases.

HIPAA-Health Insurance Portability Act Research Training Course.

Human Research Curriculum certification through CITI Collaborative Institutional Training Initiative.

Training in the CWIQ software and TELEform (industrial scanning software program) for administering the CWIQ (Core Welfare Indicator Questionnaire) Survey.

Worked with other specialized surveys including the Survey of Living Conditions (SLC) and the Household Budget Survey, which are both widely implemented across the Caribbean.

Computation and implementation of poverty indicators such as expenditure related quintiles, poverty gaps, gap ratios and Gini indices/Lorenz Curves to inform policy.

AWARDS

Fellowship Award from the School International & Public Affairs, Columbia University, for academic achievement (2006-2008)

Departmental Award for best performer in Economics (B.A. Degree Conferral, May 2004)

Island Scholar Grenada 2002; scholarship for college awarded.



Contact this candidate