Data Scientist • Industry 4.0

Turning Data into
Industrial Impact

Specialized in lean, production-ready pipelines for process optimization and automation in manufacturing environments.

93%
Model Accuracy
70%
Faster Training
Capex Avoided
₹1.2Cr
Hardware replacement
Efficiency Gain
75%
Faster preprocessing

Featured Projects

Production-ready solutions with measurable business impact

📈

OBA Consumption Optimization

ML regression pipeline replacing ₹1.2Cr hardware sensors with 93% accurate brightness predictions.

Python Polars Scikit-learn MLOps
₹27.5L
Annual Savings
93%
R² Score
📄

PDF Classification Engine

Computer vision pipeline automating QA team's manual PDF sorting using FFT and Hough analysis.

OpenCV PyMuPDF FFT NumPy
0.8s
Per File
95%
Accuracy
⚡

Payroll Automation Engine

Custom Python engine replacing 1-day manual payroll process with instant, error-free calculation.

Python Pandas Automation
24h→24s
Processing Time
Zero
Errors

Technical Expertise

Tools and technologies I work with

Core Languages

Python SQL Bash

Data Processing

Polars Pandas NumPy DuckDB Apache Parquet

ML & Analytics

Scikit-learn Power BI PI Vision Regression

Computer Vision

OpenCV PyMuPDF FFT

MLOps & Tools

Git PyInstaller Cross-validation

Project Timeline

Nov 2024 - Dec 2025

Nov 2024
OBA Reduction Initiative
ML pipeline development & validation
Jan 2025
Tech Stack Migration
Pandas → Polars (70% performance gain)
Mar 2025
PDF Automation
QA process automation deployed
Jun 2025
Payroll Engine
Full automation in production
Sep 2025
OEE Dashboards
Real-time monitoring deployment
Dec 2025
Mobile Integration
Control room data on handheld devices