Data Scientist Senior

David R. Scott

Senior Data Scientist/AI Implementation Lead

**** ********* ****

Baltimore, MD 21209

412-***-**** (C)

E-Mail: *******@******.***

Summary:

I specialize in creating value and insight with practical, actionable Analytics and fully developed Artificial Intelligence solutions. I can help you gain insight and prepare for the future with more confidence.

I possess extensive expertise in data science and AI product development of Large Language Models (LLMs) for complex NLP tasks. Proven AI Strategy Analyst in cloud computing environments like AWS and MS Azure. My contributions have significantly improved workflow efficiency and yield key insights for both federal government agencies and the private healthcare industry.

I am adept at developing and deploying teams who build advanced statistical tools, Generative AI/LLM Chatbot Agents, advanced Retrieval-Augmented Generation tools, Auto Text Summarization tools, Vector Databases, and Machine Learning Forecasting solutions for the US healthcare industry.

Key Skills and Achievements:

Designing and building innovative and Military Supply Chain Analytics applications for the US Department of Defense

Guiding AI strategy and Developing AI/ML applications in AWS, Databricks and other cloud-based environments for the Healthcare, Defense, and Insurance industries.

Applying Natural Language Processing algorithms, queueing optimization models and supply forecasting models to working applications for the US Center for Medicare and Medicaid Services (CMS) and Department of Defense

Proficiency in LLM application development tools including openai/gpt4/gpt4o, transformer models (BERT, RoBERTa), vector database implementation (Pinecone), full-text search databases (ElasticSearch, OpenSearch), Advanced Prompt Engineering (DSPy), as well as pydf, nltk, tiktoken, pyTorch

Programming in Python, R, SAS, Spark SQL, Markup and JavaScript

Writing technical aspects of analytics work for a variety of successful RFP Responses

Certified SAFe 5 (Agile Development)

Federal Government Clearance: Public Trust, Interim Secret

Specialties – Healthcare Industry:

AI/LLM applications for large-scale document analysis

Data Strategy development for CMS/CCSQ’s ISG systems

Co-development (as team AI Implementation Lead) of various advanced ML models (e.g., Deep Learning) as potential alternatives to current CMS Medicare Advantage (Part C) HCC-based Risk Score regression payment models, for CMSs Center for Medicare and Medicaid Innovation (CMMI)

Experienced in Cloud Computing Data Science tools and services including AWS (Amazon Bedrock, Lambda, SageMaker, Clarify, Textract, Q Developer, Q in QuickSite, Kinesis) and Microsoft Azure (Azure DevOps, Azure OpenAI, AI Search, Document Intelligence)

Proficient in efficiently managing and optimizing cloud resources and LLM token utilization to maximize performance and cost-effectiveness

Extensive applied research and analysis of standard CMS Risk Adjustment methods and their Machine Learning alternatives

Automatic Diagnostic Code identification NLP models (BERT and BIOBERT word tokenizers applied to OCR-scanned EHRs for Diagnosis inference)

Financial forecasting and actuarial trend analysis for Medicare Advantage insurers

Comprehensive Population Health Management Analytic Dashboards for provider networks

20+ years’ experience analyzing Healthcare claims and Electronic Health Records data

Experience working in CMS IDR data

Trained in Large Language Model (LLM) advanced Prompt Engineering and Retrieval-Augmented Generation (RAG) methods, and other Generative AI Techniques

Detailed RFP written responses for large-scale CMS analytics projects

Specialties – Defense Industry:

Naval Aviation Supply Chain Forecasting and Analytics

Aircraft time-to-repair and Readiness agent-based simulations and predictive models

Data Science project management in Azure DevOps environment

Specialties - Other Industries:

Classification and regression models for vehicle fleet maintenance and customer churn (e.g., random forests, SVM, polynomial regression, etc.)

Queuing Theory Optimization Methods and Models in the U.S. Social Security Disability Appeals Judicial System

Discrete Time Markov Chains

Telecom-Banking fraud detection algorithms

Time series forecasting

Customer sentiment natural language models

WORK EXPERIENCE

Senior Data Strategist

Tantus Technology

December 2022 – Present

Innovation Lab Co-lead for CMS/CCSQ Information Systems Group

AI Development Lead for Tantus’ InsightsAI product team

Data Strategy lead for CMS/CCSQ Central Data Repository development team. Data Development in Databricks and SAS Viya using Spark Clusters and AWS S3 buckets

RFP Response proposal team analytics lead

Lead AI/LLM developer for Tantus’ InsightsAI product

GPS Strategy and Analytics Specialist Master/AI Implementation Lead

Deloitte Consulting

October 2021 – December 2022

Multiple roles developing Artificial Intelligence (AI) products, including:

AI Implementation Lead for CMS/CMMI Risk Score Methodology Development project

oMigration pipeline development for very large data sets related to Medicare enrollees from CMS’ Integrated Data Repository (IDR) into CMS cloud instance, including claim diagnoses, free text, billing, enrollment, prescription, provider and member data, along with other electronic health records, and many external data sets

oExtensive data transformation for model feature development, engineering of extremely disparate data elements into a single data model that is cohesive and coherent for AI model development, in CMS DataBricks Notebooks.

oData validation metrics and comprehensive Data Dictionary development.

oExtensive AI model testing and validation

oCareful analysis of data quality, enrollee privacy, equity considerations during feature engineering and model development

Lead AI/Data Science practitioner for Deloitte’s AI for Medical Records product development team.

Co-developer of AI for Medical Records Text Analytics Platform

Solutions Architect, Deloitte AI Exploration Lab AI Rapid Development team

Chief Data Scientist,

Naval Systems, Inc. (Federal Government contactor)

October 2020 – October 2021

Lead role responsible for development of Data Science applications for NSI products and services, and oversite and development of the Data Science and Simulation & Modeling teams within NSI.

Development of Data Models including feature engineering, for data models used in predicting F-15 supply chain lapses via machine learning algorithms

Supporter and Developer of various other Naval Aviation supply chain data models for supply chain forecasting.

Agile Development scrum-master for large and complex analytics projects with multiple workflows and complex and dynamic customer requirements.

Senior Consultant Data Scientist,

CGI Federal (Federal Government contactor)

October 2019 – September 2020

Worked as a Senior Data Scientist contractor within SSA’s Analytics Center of Excellence (ACE)

Responsible for creating and deploying productivity optimization models for SSA Administrative Appeals Judges who decide a high volume and variety of disability case appeals.

oDeveloped data and analytic model to measure productivity of key high-level SSA employees.

Other work includes development and analysis of improper payment metrics related to SSA beneficiaries, and the related data models.

Data Scientist,

RELI, Inc. (Healthcare Analytics and IT contactor)

July 2018 – October 2019

Worked as a Data Scientist responsible for key aspects of operational analytics and ML solutions pertaining to RELI's role as a CMS Risk-Adjustment Data Validation (RADV) consulting contractor.

Develop and implement NLP algorithms to read unstructured payer documentation to identify patterns related to potential fraud, waste, and abuse. Product development consultant for reporting and analysis proposals.

CMS proposal response writer for RELI’s responses to data architecture, data science and advanced analytics TO responses.

Senior Consultant, Healthcare

d-wise (Healthcare Analytics and IT contactor)

January 2018 – July 2018

Worked as Data Analytics Consultant playing key role in team responsible for building provider web portal, to measure and visualize healthcare provider performance for a major Blues plan in the Northeast US.

Role includes extensive development in the SAS and JavaScript programming languages.

Manager, Corporate Analytics

Informatics

Lumeris (Population Health Management Consulting)

July 2017 – December 2017

Worked as a Data Scientist and Analytics Lead responsible for measuring, analyzing, understanding, predicting, and communicating all key findings related to patient health measurement outcomes and associated costs, for Major Mid-Atlantic Health system associated with one of Maryland’s largest Hospital networks.

Risk Adjustment factoring and Medical and RX IBNR estimation across a variety of contractual assumptions

Lead for Population Health Management COPD and opioid patient program evaluation studies.

Senior Consultant

Decision Science Practice

CenturyLink-Cognilytics (Analytics Consulting)

September 2012 – July 2017

End-to-end project management as well as analytic and technical work for advanced analytics and statistical consulting engagements in US industry, including statement of work language, RFP responses.

Data Scientist role included model building and validation, model programming code (primarily in R, Python and SAS), data visualization (primarily with R and SAP Lumira), machine learning algorithm selection and implementation, forecasting methods, queuing theory models

Fraud detection modeling, database implementation of predictive models, and communication of results to C-level executives.

Experienced user of SAS, R/RStudio, Python Statistical and Data Science applications; Microsoft Azure; and SAP HANA Cloud, SAP Predictive Analytics software, and related SAP products and services.

Projects and results include:

Co-developed Natural Language Processing application to analyze customer sentiment, and timely and accurate sales forecast models incorporating a variety of novel customer data, within SAP HANA Database developed for one the world’s largest retail apparel companies.

Led and managed the building of a predictive model applied within a large hospital system database, which accurately predicted readmission likelihood for patients, enabling measurably more efficient patient aftercare resource allocation.

Co-developed a predictive model of disability claim allowance likelihood and discovered Social Security Administration disability claimant appeal resolution time and case outcome drivers. Used the scored predictions to design priority queuing system built from the scored predictions, with estimated reduced claimant wait times, allowing processing of over 100,000 more cases per year.

Co-developed operational prototype to calculate a patient health score, i.e., a credit score-like measure of member’s health, for one of the 3 largest health insurers in the US. The new approach proved many times faster than the prior method of calculation and allowed the client to being making the calculation in-house for the first time.

Developed end-to-end customer churn analytics environment for one of the largest satellite internet service providers in the US. This work generated a variety of actionable insights into customer and competitive data, resulting in the customer reaching their annual churn reduction goal in the 1st quarter of the year, and creating bottom line impact to revenue growth.

Various roles: mentorship of CTL-Cognilytics’ global analytics team in Gurgaon, India, including software demonstration webinars and co-authorship of analytics software training materials; creation of use case demonstrations of SAP’s Predictive Analytics product for large corporations in the Health Care, Telecommunications and Oil and Gas industries.

TRAINING/CERTIFICATIONS

3 AWS Certificates in LLM skills (Amazon Bedrock and Amazon Q, Foundations of Prompt Engineering) July, 2024

EdX Large Language Models: Application through Production January 2024

Introduction to AWS Kinesis, April, 2023

MITx Supply Chain Fundamentals, June, 2021

https://courses.edx.org/certificates/27f46cdf10df4025b6ceb6592cd6ad01

MITx Supply Chain Analytics, March, 2021

https://courses.edx.org/certificates/e3c4872860dd4817bfd7e648ef8f5839

IBM Blockchain Essentials, January, 2021

https://courses.cognitiveclass.ai/certificates/020bd98ffe674f089e132059fa5ef3d4

Machine Learning Certificate - Stanford Online (2018)

https://www.coursera.org/api/certificate.v1/pdf/ZWB78U3E5MS2

Data Science Certification - Johns Hopkins University on Coursera (2017)

DISC Consulting Skills (2009)

EDUCATION

Bachelor of Science:

University of Tennessee- Chattanooga

GPA: 3.2/4

Major: Applied Mathematics

Minor: Economics

ORGANIZATIONS

Society for Industrial and Applied Mathematics

https://www.siam.org

Contact this candidate