Data Scientist · Machine Learning Engineer · Data Analyst · Forward Deployed Engineer

Bharath Naveen

I turn messy data into decisions and ship the production systems teams depend on. Data science, machine learning, and analytics, taken end to end, from exploratory analysis to deployed models on AWS.

MS Machine Learning · Arizona GPA 3.89 3+ yrs on Microsoft products Production ML on AWS Client-facing · cross-functional
Portrait of Bharath Naveen Tucson, AZ
0.93 AUC
Best predictive model, across 50K+ samples with full model evaluation
~3 days
Manual effort cut per cycle through SQL & Python automation
2
Production systems live on AWS: an ML pipeline and an analytics platform
480+
Test cases and defect records analyzed per cycle for Microsoft stakeholders
01

Selected work

End-to-end data science and machine learning projects, from exploratory analysis and feature engineering through to deployed, production systems. Each one leads with the problem it solves; the technical detail sits underneath.

Machine Learning · NLP Containerized · AWS Production-deployed

Phishing Detection System

An ML system that catches fake and malicious websites the moment they appear, before a blocklist ever hears about them. It reads a live page the way an analyst would, then returns a clear safe / suspicious / phishing verdict with the reasons behind it. Built as a containerized microservice and deployed on AWS, with supervised models, LLM-based brand-impersonation detection, and full model evaluation.

0.933
Best model ROC-AUC
50K+
URL samples
4
Models benchmarked
4-layer
Analysis pipeline
PythonLightGBMXGBoostRandom ForestFeature engineeringPlaywrightBeautifulSoupLLM integrationStreamlitDockerAWS ECR/ECS
View on GitHub Explainable verdicts through a deterministic Evidence Adjudication Layer.
Live in production Data Engineering · Serverless AWS University of Arizona

Cohort Analytics Platform

A live analytics platform the university relies on to track student cohorts, built on a serverless AWS backend that turns raw records into dashboards staff use every day. I built the data and cloud layer end to end: the ETL pipelines, the database access patterns, and the CI/CD deployment behind it, working directly with university stakeholders to ship it.

Live
In daily production use
Serverless
Lambda ETL + DynamoDB
CI/CD
Multi-environment pipeline
AWS LambdaAPI GatewayDynamoDBDAO patternsContainerized ETLCI/CD
Visit the live site Running at cohort.bi.arizona.edu.
Data Analytics · SQL Data modeling

BN Motors Database

An end-to-end dealership database that turns raw inventory, sales, and customer records into business-ready analytics. Designed from the ER model up into a fully normalized schema, with complex SQL (joins, aggregations, window functions) driving the reporting views a decision-maker can act on.

SQLER modelingSchema designWindow functionsBusiness reporting
Predictive Modeling Classification · Imbalanced data

Loan Default Prediction

A model that flags which loans are likely to default so a lender can price risk before it hits the books. Built with careful exploratory analysis, feature engineering on economic variables, and model selection tuned to the false-positive / false-negative trade-off that actually costs money.

PythonLogistic RegressionRandom ForestXGBoostEDAFeature engineeringROC-AUC / precision / recall
02

Experience

Three years at Tata Consultancy Services on the data and analytics side of Microsoft products: a client-facing, cross-functional role owning the dashboards, SQL, and Python automation that stakeholders made release decisions from.

System Engineer, Data & AnalyticsMicrosoft account · TCSApr 2023 – Aug 2024

Built two Power BI dashboards from scratch (bug-report tracking and feature-delivery progress) that Microsoft stakeholders used to make release calls, replacing manual update cycles entirely. Automated SQL querying and Python data collection, cutting about three days of manual effort per reporting cycle, and ran exploratory data analysis across 300+ test cases and 180+ defect records each cycle for a cross-functional team of eight, translating findings into clear, stakeholder-ready reporting.

Associate System EngineerMicrosoft account · TCSJul 2022 – Apr 2023

Led two analysts on delivery and data-quality standards, built automated workflows that cut manual data collection, and turned defect-trend analysis into recommendations that measurably improved system reliability and issue-resolution speed.

EngineerTCSApr 2021 – Jun 2022

Executed 300+ structured test cases across enterprise environments, documenting results to support data-driven reporting and building foundations in structured problem-solving and large-scale data validation.

03

Résumé

The full picture, right here on the page. No download required.

Bharath Naveen résumé, page 1 Bharath Naveen résumé, page 2
Download PDF Tap a page to view it full size
04

Toolkit

The tools and methods behind the work above.

Languages & ML

PythonSQLRscikit-learnXGBoostLightGBMRandom ForestNeural Networks

Methods

Exploratory data analysisFeature engineeringStatistical modelingPredictive modelingModel evaluation

NLP & LLMs

Applied NLPNLTKTF-IDFLLM integrationRAG pipelines

Data & BI

pandasNumPyPower BIPlotlyStreamlit

Cloud & Data Engineering

AWS (Lambda, DynamoDB, API GW, S3, ECR/ECS)DockerCI/CDETL pipelinesER modelingMySQLPostgreSQL

Web & Automation

PlaywrightBeautifulSoupWorkflow automation
05

About

I am a data scientist and machine learning engineer who likes owning the full arc of a problem: taking something ambiguous and messy, doing the exploratory analysis to understand it, and building it all the way through to a deployed system other people can depend on.

I hold a Master’s in Machine Learning (University of Arizona, GPA 3.89) and spent three years before it at Tata Consultancy Services on the Microsoft account, in a client-facing role turning raw data into decisions and shipping the pipelines and reporting behind them. That mix, technical depth plus working directly with stakeholders, is exactly what data science, analytics, and forward-deployed roles ask for. I am open to relocating.