Aryan Chaubey

Data Engineering & Analytics

Rising senior at Texas A&M University studying Data Engineering, with minors in Computer Science and Statistics. I build ML prediction systems, data harmonization pipelines, and the full-stack tooling around them.

──01.experience12ms

01 — Experience

Where I've worked

Building analytics infrastructure and predictive models in industry.

Data Analyst Intern

LTIMindtree·Retail & Consumer Packaged Goods

Present

raw retail data→ETL + modeling→dashboards + forecasts

Building analytics pipelines and predictive models for retail and CPG clients.

pipeline latency−32%

forecast accuracy+18%

—Developed dashboards and reporting workflows to surface key business metrics across retail channels.
—Optimized ETL pipelines for faster data ingestion and reduced processing latency.
—Built predictive models to forecast demand and support merchandising decisions.

──02.stack12ms

02 — Stack

Tools & technologies

The stack behind the pipelines.

$ ls -la ~/stack/

languages/

-rw-r--Python— pipelines, modeling
-rw-r--TypeScript— web, tooling
-rw-r--SQL— analytics, ETL
-r--r--R— statistics

ml/

-rw-r--XGBoost— ProEdge, KalshiEdge
-rw-r--LightGBM— PRISM quantile models
-rw-r--scikit-learn— calibration, baselines
-rw-r--Pandas— feature engineering

data/

-rw-r--PostgreSQL— signal + prediction stores
-rw-r--PostGIS— AEGIS spatial queries
-rw-r--Redis— hot signal cache
-rw-r--SQLite— PRISM local box scores
-r--r--Parquet— historical game store

backend/

-rw-r--FastAPI— prediction + twin APIs
-rw-r--Pydantic— schema validation
-rw-r--WebSocket— live order book streams
-rw-r--Docker— local + deploy parity

frontend/

-rw-r--Next.js— AEGIS digital twin
-rw-r--React— PRISM scanner UI
-rw-r--Tailwind— design systems

ops/

-rw-r--Prometheus— model + API metrics
-rw-r--Grafana— monitoring dashboards
-rw-r--GitHub Actions— CI, eval scoring
-r--r--Tableau— LTIMindtree dashboards

──03.projects12ms

03 — Projects

Selected work

Media tools, supply chain simulation, and analytics systems.

NNW Media Intelligence Platform

Six connected systems take a creator network from finding collaborators to publishing finished clips.

Media IntelligenceData EngineeringAutomation

MultiPOV Studio

A Mac editor for syncing recordings, switching camera angles, and cutting highlights on one timeline.

Video EditingmacOSMedia Engineering

AEGIS

A supply chain simulator that maps disruptions, estimates inventory risk, and proposes a reroute.

nodes40+

tools8

evals10

LLM AgentsPostGISOptimization

ProEdge matchup board comparing market totals and model estimates

ProEdge Analytics

Compares NFL, NBA, and MLB scoring forecasts with market totals and shows the model’s uncertainty.

features200+

sports3

models2

Predictive ModelingMLOpsFastAPI

ROSETTA

Turns differently formatted retailer sales files into one schema with repeatable transformations.

cases18

modeoffline

calls/row0

Data EngineeringLLMETL

KalshiEdge

Compares BTC and ETH market probabilities with model estimates and simulates fills in paper mode.

workers4

features9

modepaper

Prediction MarketsMLReal-time

PRISM

Scans NBA player props using local box scores and shows a prediction range for each estimate.

storageSQLite

modelsquantile

runtimelocal

Sports AnalyticsLightGBMFull-stack