Kumar Saksham Saksham3124

Hi 👋, I'm Kumar Saksham

🔭 Built end-to-end analytics systems in compliance, operations, and finance — actively seeking analyst roles
🤝 Looking to collaborate on data analysis, business intelligence, SQL, or dashboard projects
📍 Open to Data Analyst roles
💬 Ask me about SQL window functions, anomaly detection, Power BI, Tableau, Python for data analysis
⚡ Fun fact: I built a 3-layer GST fraud detection system that flags 15% of 50,000 invoices — using pure SQL and statistics, no ML

Languages

Data & Analytics Libraries

Databases

BI & Visualization

Tools

End-to-end analytics system detecting fraudulent GST invoice patterns across 50,000+ records

3-layer detection pipeline — Rule-based validation → Statistical anomaly detection → Weighted risk scoring
SQL window functions for Z-score analysis, rolling average spike detection, and IQR outlier detection
Flags 7,512 invoices (15%) as suspicious, identifies 35 HIGH-risk vendors out of 210
Interactive Tableau dashboard — 🔗 View Live
Stack: Python · PostgreSQL · SQL · Pandas · Tableau

End-to-end SQL analysis of 100,000+ orders identifying delivery failures, geographic risk patterns, and seller accountability gaps

8.11% late delivery rate across 96,470 delivered orders — Northeast Brazil states show 2–3x the national average
Late delivery causes a 40% collapse in review scores (4.29 → 2.57), directly quantifying business impact
Seller risk tiering using CASE-based classification across delay rate, revenue exposure, and review impact — built on a 7-table normalized PostgreSQL schema
Live Tableau dashboard with state-level map, monthly trend, and seller risk breakdown — View Dashboard →
Stack: PostgreSQL · SQL · Tableau Public

Automated data pipeline simulating real-time railway delays with risk classification

⭐️ From Saksham3124