psql · sumit_prajapat=# — analyst workbench
sumit=# SELECT * FROM analysts WHERE role IN ('data_analyst','bi_developer') AND certified = TRUE LIMIT 1;

Sumit Kumar Prajapat

Data Analyst
(1 row) ✓ 0.042s · Rajasthan, India · open to Data Analyst & BI Developer roles

I build end-to-end analytics — Azure pipelines into SQL warehouses into Power BI dashboards into ML models — and turn raw data into decisions a business can act on.

▶ View projects ↓ Download resume in ↗ LinkedIn ✉ Contact me
-- career_stats · all numbers from shipped work
certificationsrecords_modeleddax_measuresend_to_end_builds
5×558K+40+6
~/about.md · last modified: today

$ whoami

I turn raw data into decisions a business can act on — end to end, no handoffs. Five industries, six production-grade builds.

I own the full chain: Azure pipelines → SQL star schemas → Power BI → ML models. Retail, Finance, Healthcare, E-Commerce, Education — different data, same discipline: every dashboard ends in a decision, not decoration.

Two years on the business side of financial services means I frame findings the way stakeholders actually use them — and flag what matters before a report ships.

▸ Open to full-time Data Analyst / BI Developer roles — ready to own reporting end to end.

~/skills.yaml · # no percentage bars — every line maps to a shipped project

Stack

analytics_bi:
Power BIDAXPower QueryData ModelingData VisualizationExcel
sql_and_etl:
SQLPostgreSQLDuckDBAzure Data FactoryETL PipelinesData Warehousing
programming:
PythonPandasNumPyscikit-learnStreamlit
cloud:
Microsoft AzureAWS
machine_learning:
Forecasting · ProphetClassificationClustering · KMeansRFM AnalysisCausal Inference · DiDHypothesis Testing
web_apps:
Full-Stack WebSupabaseAuthsql.js · WebAssembly
automation:
n8nWorkflow AutomationAPI Integrations
~/projects.sql · -- SELECT * FROM projects ORDER BY impact DESC;

Featured projects

End-to-end builds: pipeline, warehouse, model, dashboard. Numbers included because they matter.

sumit=# SELECT * FROM projects ORDER BY impact DESC;
6 rows returned in 0.31s
[new] [retail] [causal-stats]live ↗ github ↗
★ latest build

Grocery Retail Analytics

24-check data-quality gate → DuckDB star schema → 13 SQL analyses → difference-in-differences with placebo tests → 5-page Power BI report (44 DAX measures) + Streamlit app with a cite-or-refuse “ask the data” assistant.

1.46Mtransactions
50.6%habitual coupons
225%display+mailer lift
58/58DAX = SQL
  • Top 10% of households drive 34.2% of sales; 318 lapsing regulars hold 13.4%
  • Placebo checks failed → campaign ROI unmeasurable; recommended a 10% random holdout
  • SQL-vs-DAX reconciliation caught 3 DAX bugs before they reached the report
stack: python · duckdb sql · statsmodels · power bi · dax · streamlit · github actions
Grocery Retail Analytics — Power BI Executive Overview Grocery Retail Analytics — Power BI Promotion Effectiveness
[ml] [azure] [healthcare]github ↗

Healthcare Provider Fraud Detection

Azure Blob → Data Factory → PostgreSQL 9-table warehouse (2.43M rows) → scikit-learn fraud model (AUC 0.9573) → 4-page Power BI report with provider drill-through.

558Kclaims
226×fraud concentration
90.1%fraud recall
$295.7Mexposure flagged
  • Top billing quartile: 34.02% fraud rate vs 0.15% in the bottom quartile
  • 96% of high-velocity providers (>10 claims/day) are fraud-flagged
  • Fraud providers file 9+ diagnosis codes 1.66× as often — diagnosis stuffing
stack: azure adf · postgresql · python · scikit-learn · power bi · dax
Healthcare Fraud Detection — Power BI Executive Overview Healthcare Fraud Detection — Power BI Fraud Detection page
[live] [finance] [forecasting]live ↗ github ↗

Mutual Fund Analytics Platform

Yahoo Finance + AMFI → Azure Blob → Data Factory → Azure SQL star schema → risk suite in Python → Prophet NAV forecasts → 4-page Power BI report and a live Streamlit app.

14,384fund schemes
51AMCs
5 + 4dim + fact tables
25+DAX measures
  • Full risk suite: Sharpe, Sortino, Treynor, alpha/beta and max drawdown
  • 30/60/90-day Prophet NAV forecasts with confidence bands
  • Azure Data Factory pipeline running end to end into a star schema
stack: azure adf · azure sql · python · prophet · power bi · streamlit
Mutual Fund Platform — Power BI Executive Overview Mutual Fund Platform — Power BI Risk & Volatility page
[warehouse] [bi] [e-commerce]github ↗

Olist E-Commerce Analytics

8 raw tables → Azure Blob → Data Factory → Azure PostgreSQL star schema (4 dims + 1 fact) → 3-page Power BI report with decomposition tree, key influencers and what-if price simulation.

112,650sales records
~97%one-time buyers
91.88%on-time delivery
40+DAX measures
  • Retention measured on customer_unique_id — only ~3% of real customers ever reorder
  • São Paulo drives 38.3% of revenue; health_beauty leads at R$1.4M
  • Remote AP state waits 28 days vs a 21-day average delivery
stack: azure adf · postgresql · sql · power bi · dax · power query
Olist E-Commerce — Power BI Sales Intelligence page Olist E-Commerce — Power BI Delivery & Operations page
[live] [ml] [segmentation]live ↗ github ↗

Customer Segmentation Engine

UCI Online Retail data → cleaning → RFM scoring → K-Means vs Hierarchical vs DBSCAN benchmarked head-to-head → PCA, CLV and cohort analysis → interactive Streamlit app.

541Ktransactions
0.52silhouette score
~40%revenue from top 15%
£127Krecoverable revenue
  • Champions are 8× the lifetime value of lost customers
  • Cohorts lose 70%+ of customers by month 3 — the window to act
  • K-Means (K=4) beat Hierarchical and DBSCAN on compact, explainable clusters
stack: python · pandas · scikit-learn · pca · streamlit
Customer Segmentation — Customer count and revenue by RFM segment Customer Segmentation — K-Means cluster scatter plots
[live] [education] [full-stack]live ↗

QueryScratch — Learn SQL by Doing

A free SQL learning platform: hand-crafted challenges from a first SELECT to recursive CTEs, with real queries run client-side via sql.js / WebAssembly and instant exact-output feedback.

500SQL challenges
0installs needed
WASMin-browser engine
Freefor students
  • No server round-trip — every query runs inside the browser
  • Learn, playground, mock-interview and practice tracks, beginner → expert
  • Streaks and per-user progress on Supabase auth
stack: sql · sql.js · webassembly · supabase · javascript
QueryScratch — QueryScratch home page
sumit=# SELECT project, domain, scale, impact FROM portfolio.builds ORDER BY scale DESC;
(6 rows · 0.018s) — headline numbers, straight from shipped work
projectdomainscaleimpact
Grocery Retail Analyticsretail1.46M transactions50.6% coupons go to habitual buyers
Healthcare Fraud Detectionhealthcare558K+ claims226× fraud concentration
Mutual Fund Platformfinance14,384 schemes51 AMCs on one risk framework
Olist E-Commercee-commerce112,650 rows40+ DAX measures
QueryScratcheducation500 questionsfree SQL sandbox for students
Customer SegmentationretailRFM + KMeanslive Streamlit app

more on github → github.com/Skpkush

~/journey.git · $ git log --oneline --reverse career

Journey

f4a91c2now: open to Data Analyst & BI Developer rolesHEAD → main
Bringing BFSI domain depth and a certified Microsoft data stack to a full-time analytics team.
b7e2c4dfeat: grocery retail analytics — 1.46M transactions
Data-quality gate, DuckDB SQL, difference-in-differences with placebo tests, and a Power BI report reconciled to SQL 58/58.
8d3e7b1feat: end-to-end analytics portfolio shipped
Three complete builds — fraud detection, fund analytics, e-commerce BI. Azure ETL → SQL → Power BI → ML.
c2a94f0cert: PL-300 · AZ-900 · DP-900 · AWS CCP · CFA-IF
Microsoft data stack, AWS, and CFA Institute investment foundations — validated ×5.
7b1d3a9job: Business Data Analyst · Financial Services
Analytics, dashboards, and n8n automation for a working financial-services business.
9a4f2e7job: Python & CS Instructor · School Administrator
Teaching tech and running operations end to end.
3e8c5d2job: Marketing Executive @ Shriram General Insurance
Ground-level BFSI: products, customers, and claims — the domain I now analyze.
1c0b8a3init: B.Com — University of Calcutta
Commerce foundation — accounting, finance, and how a business measures itself.
~/contact.json · // hiring a Data Analyst or BI Developer? let’s talk.

Contact

{
  "email": "sumitkprajapat29@gmail.com",
  "github": "github.com/Skpkush",
  "linkedin": "in/sumit-k-prajapat",
  "location": "Rajasthan, India · remote-friendly",
  "status": "open_to_work"
}

// opens your email app with the message pre-filled

⎇ main ● open to work Ln 1, Col 80 UTF-8 SQL