Hi, I’m Sachin Otsuka Arjun.

Evidence over opinion: Analytics, Experiments, and ML.

ABOUT ME

I’m a Data Analyst, Data Scientist, and Machine Learning Engineer passionate about solving complex problems at the intersection of AI, analytics, and sports. I’m currently pursuing my Master’s in Applied Analytics at Columbia University, where I specialize in transforming raw data into actionable insights and building scalable machine learning solutions.

I thrive in fast-paced, collaborative environments where I can invent, iterate, and lead projects from concept to impact. Whether it’s evaluating AI models, optimizing data pipelines, or blending qualitative and quantitative insights, I’m motivated by building systems that make a measurable difference.

When I’m not working with data, you’ll probably find me on the football pitch (soccer!), exploring NYC, or brainstorming the next big idea that bridges sports, technology, and AI.

Download Résumé View Projects
Portrait of Sachin Otsuka Arjun

Work Experience

Data Engineer — PrivateBlok

Aug 2023 – Jul 2024 · Bengaluru, India

  • Architected a scalable relational store integrating MCA + external APIs, consolidating structured & semi-structured data from 1,000+ Indian Pvt Ltd companies for faster access and analytics.
  • Built multithreaded scraping & ETL pipelines, boosting extraction speed by ~400% and cutting cycle time to near real-time for downstream teams.
  • Implemented end-to-end data quality checks (anomaly detection/QA), achieving 99%+ accuracy and improving cross-team productivity by ~20%.
  • AI
  • Excel
  • Web Scraping
  • APIs
  • Data Quality
  • Data Integration
  • Database Management

Web Development Intern — CoachEd

Sep 2022 – Oct 2022 · Mysore, India

  • Developed a dynamic Restaurant-Reservation website using HTML, CSS, Sass, JavaScript, and Bootstrap.
  • Improved responsiveness for seamless behavior across device sizes and viewports.
  • Ran code reviews and integrated best practices to strengthen performance and security.
  • HTML
  • CSS/Sass
  • JavaScript
  • Bootstrap

Projects

NYC Neighborhood Insights Dashboard

Geo-Spatial Analysis of NYC Neighborhoods

Conducted geo-spatial analysis of NYC neighborhoods to help first-time residents overcome decision paralysis (~300k movers/year). Built cross-sectional datasets via ETL from Google Maps API, Zillow Research, NYC Open Data, and SimpleMaps; delivering personalized recommendations and on an interactive Tableau dashboard.

  • APIs
  • Tableau
NYC-Crime Analytics – End to End Retrieval System

NYC Crime Data Analytics Platform

Engineered a full-stack pipeline for 10M+ records: PySpark ETL, MongoDB/Postgres storage, Neo4j network views, and a Flask UI for hotspot detection and clustering—turning raw incidents into actionable city-safety insights.

  • PySpark
  • MongoDB
  • Postgres
  • Neo4j
  • Flask
MLS Soccer Analytics – Archetype & Anomaly Detection

MLS Soccer Analytics & Player Profiling

Linked physical traits to performance (xG, assists, points added) with clustering to find archetypes and position misfits. Produced scouting shortlists and development cues using 2024 MLS data.

  • R
  • Clustering
  • xG
  • Scouting
Kaggle Competition

Predictive Modeling of Click-Through Rate(CTR) Using Advanced Machine Learning Techniques

Built a CTR prediction pipeline that cleaned mixed ad data, handled missingness, and engineered campaign signals to turn raw logs into decision-ready metrics. Benchmarked linear, tree, and RF models, selected tuned XGBoost for the best RMSE on a held-out scoring set

  • Experiment Design
  • Simulation
  • Cost Analysis

Skills

Core

  • Python, R, SQL, C Programming
  • HTML, CSS, JavaScript
  • Cloud: Amazon Web Services(AWS), Microsoft Azure

Frameworks: Data & ML

  • Tableau, Neo4j, Docker, MongoDB, Spark, MySQL, PostgreSQL
  • Tensorflow, Scikit-learn, NumPy, PySpark, Pandas, Git, Postman, REST API, JSON, HTTP

Hobbies and Languages

  • Hobbies: Football(Soccer), Basketball, Baseball, Hockey, Golf, Music, Travelling
  • Languages:English, Native; Japanese, Native; Hindi, Fluent; Kannada, Fluent

Contact

Quickest way to reach me:

LinkedIn Email me