Water. Earth. Fire. Air.
Business & Data Analyst · Applied AI/ML Researcher, bending raw data into decisions.
Long ago, data and business lived in harmony. Then everything changed when the spreadsheets attacked. My journey began with a childhood question about how computers think, answered in binary, and grew into an All-India Rank of 5024 among a million JEE aspirants, a CS degree at NIT Warangal, a master's at Oklahoma State, and a first paper presented at IEEE FUZZ 2023 in Incheon, South Korea. I build intelligent systems where machine learning, data science, and optimization meet: robust, explainable, and pointed at real-world problems.
▼ scroll to begin the journey
Book One
I support consultants and technical teams through every stage of a project: design, architecture, development, configuration, and deployment; and translate between business partners and technology teams so nothing is lost in the fog of war.
Inherited a one-PDF-at-a-time research prototype and carried it to a production pipeline digitizing 570K+ historical Oklahoma well records under Prof. Priyank Jaiswal (DOE Anadarko Basin Carbon Management Hub): 51K+ wells live on an interactive map, poster presented at AAPG Tulsa 2026. Read the case study →
Supported research and instruction while finishing my master's; TA for Discrete Mathematics, leading class discussions, grading, and mentoring students. Where the theory met the chalkboard.
Built and deployed data-driven solutions with Python and SQL; created dashboards and reports in Excel with advanced macros; managed multiple initiatives independently and presented findings to senior leadership.
M.S. Computer Science - Oklahoma State University (2023–2025), GPA 3.64
B.Tech Computer Science - National Institute of Technology, Warangal (2019–2023)
Book Two
Each one a battle. Each one a lesson.
Research project digitizing 570,953 scanned oil & gas well records (1911–2024): OCR, OpenCV grid detection, and U-Net segmentation resolve each well against a 4.5M-cell PLSS PostgreSQL database, with human-in-the-loop corrections applied automatically via GitHub Actions. ~4,900 wells on a live map and growing. Literally bending earth data.
Medallion-architecture warehouse on SQL Server + Azure Data Factory integrating 10+ sources: cut manual prep 60%, improved pipeline efficiency 40%, with star-schema models and real-time Power BI dashboards.
View on GitHub ↗Master's research into biologically-plausible computation: S&P 500 index segments encoded as spike trains and classified with LIF and Izhikevich neuron simulations; thesis, poster, and full simulation code in the repo.
View on GitHub ↗React + TypeScript frontend with a Python Flask REST API that recommends movies from the MovieLens 100K dataset by matching user demographics to similar viewers; data processing with Pandas and NumPy.
View on GitHub ↗End-to-end analytics flow: scraping live cricket statistics with BeautifulSoup, cleaning and shaping in Pandas, and delivering interactive Power BI dashboards for trend analysis.
View on GitHub ↗NLP pipeline clustering players into batsmen, bowlers, and fielders from free-text descriptions: TF-IDF (1–3 grams), StandardScaler, then PCA and t-SNE projections; reading the wind in unstructured text.
View on GitHub ↗Book Three
Four disciplines. One analyst.
Flow & adaptability: analytics
Solid foundations: data engineering
Power & precision: code
Freedom & communication: process
Epilogue
The fastest way to reach me across the four nations.