Principal Data Scientist

Akshay Suresh

Data Science · Applied AI

I build applied AI/ML systems to solve business problems.

See selected work LinkedIn GitHub
Portrait of Akshay Suresh

About

Cross-domain leader

Startup → Consulting → Operational Analytics

I frame business problems as math problems and work with cross-functional teams to ship production systems.

Today, that means streamlining medical claims processing through monitoring, automation, and copilot-based solutions.

Impact

At a glance

Scale, savings, and tenure at a glance.

10+ yrs in software engineering & data science
20–25 people supervised across delivery teams
0.7M claims automated through AI, per year
~$3.3M incorrect payments prevented, 2024

Selected work

Selected projects

Outcomes up front — Expand for details.

Financial comment automation

Gen AI for claims Operational Analytics CVS Health · 2025
Automates recommendations for up to ~200K financial comments / year

Context

Financial comments are contract clauses with free-text instructions for processing claims.

Job to be done

How might we apply those instructions to a claim and produce a recommendation?

Methodology

  • KAG (Knowledge Augmented Generation) for enterprise concept vectors
  • NER on financial comments to tag concepts
  • Decision flows for how concepts interact

Outcome

  • Live claims pipeline that generates recommendations
  • Bot applies recommendations to adjudicate claims
  • ~200K financial comments automated annually

Benefit automation

Gen AI for claims Operational Analytics CVS Health · 2025
Phase-wise expansion supporting up to 0.5M claims annually

Context

Complex member benefits cause claims to drop to manual processing.

Job to be done

How might we identify and apply the correct benefit for a claim?

Methodology

  • Multi-step Gen AI framework to identify the correct benefit
  • Convert benefit instructions into structured format

Outcome

  • Live recommendation pipeline + adjudication bot
  • Supports up to 0.5M claims annually through phased expansion

Intelligent monitoring

Anomaly detection at scale CVS Health · 2024
Ensemble monitoring for claim-processing pattern shifts

Job to be done

How might we detect changes in claim denial and payment patterns?

Methodology

  • Ensemble of Isolation Forest, CatBoost, and baseline averages
  • Detects changes in claim processing patterns

Outcome

  • Trend charts and dimensional drilldowns
  • Examples for detailed investigation

Contract analytics platform

Cost & contract analytics CVS Health · 2021
Competitive insights across 500+ hospitals + auto-generated PPT

Job to be done

  • Determine competitive position in a market
  • Support contract negotiations with analytics

Outcome

  • Tableau dashboard for 500+ hospitals
  • App that generates formatted PPT with insights and recommendations

Career

Experience

Startup → consulting → healthcare DS leadership.

2026 — Present
Principal Data Scientist

Aetna, a CVS Health Company · Supervise team delivery & technical direction

2023 — 2026
Lead Data Scientist

Aetna, a CVS Health Company

2021 — 2023
Senior Data Scientist

Aetna, a CVS Health Company

2019 — 2021
Data Scientist

Aetna, a CVS Health Company

2018
Data Scientist Intern

The Boston Consulting Group

2017 — 2019
M.S. in Data Science

Northeastern University

2015 — 2017
Software Developer

Unotech Software Pvt. Ltd.

2011 — 2015
B.E. in Computer Science

University of Mumbai

Labs & libraries

Open-source libraries

Earlier experiments and packages.

Rcane

Numeric optimization for linear regression — batch, SGD, mini-batch, coordinate descent, plus a web UI for hyperparameters.

View on GitHub →

d3-charts

Higher-level abstraction to embed basic graphs and charts in web pages with d3.js.

View on GitHub →

CaraML

Simple, intuitive implementations of core machine learning algorithms.

View on GitHub →

Let’s connect

Email LinkedIn GitHub