MS Data Analytics | Webster University (Dec 2024) Piscataway, NJ | Open to US opportunities (Remote & Relocate) | STEM OPT Active

I build data-driven solutions that solve real business problems - not just notebooks that sit on a laptop.

7+ years of combined experience across healthcare, recruitment, and business analytics - including managing data relationships with 30+ NHS hospitals in the UK. Now applying that domain knowledge to data science.

Lean Six Sigma Black Belt - I don't just find problems in data. I frame them as business solutions.

Track 1 - Analytics Roles: Data Analyst · Business Analyst · Healthcare Analyst · BI Analyst Track 2 - Healthcare Recruitment: Account Manager · Client Success Manager · Workforce Analytics Manager

7+ years managing NHS hospital accounts + MS Data Analytics + LSS Black Belt

One new project published every other week. Building in public.

Analyzed 9.6M real US Medicare records to identify physician staffing gaps across all 50 states

• Processed 1.1M unique providers across 104 medical specialties
• Built interactive 5-tab Streamlit dashboard with US choropleth maps
• Applied Lean Six Sigma DMAIC framework to structure recruitment gap analysis
• Identified Wyoming (97.7%), Vermont and Alaska as most critically underserved states
• Full analysis run locally on 9.6M records - dashboard shows 50k representative sample
• Live: https://karan-healthcare-analytics.streamlit.app
• Stack: Python · Pandas · Plotly · Streamlit · CMS Medicare Data

End-to-end ML pipeline predicting 30-day hospital readmission risk - 101,745 real patient records

• Trained and compared 4 models: Logistic Regression, Random Forest, Gradient Boosting, XGBoost
• XGBoost selected with ROC-AUC 0.598 - best balance for imbalanced medical data
• SMOTE oversampling to handle 11.2% minority class imbalance
• SHAP explainability showing clinicians exactly why a patient is flagged high risk
• Live patient risk predictor with gauge chart and clinical recommendations
• Live: https://karan-healthcare-ml.streamlit.app
• Stack: Python · XGBoost · SHAP · SMOTE · Streamlit · UCI Diabetes Dataset

Analyzed 180,519 real orders - found that 57% of deliveries are late across 23 global regions

• Only 42.7% on-time delivery rate - Central Africa worst at 60.7% late rate
• 15 SQL queries via SQLite covering late rates, revenue, customer segments
• ABC inventory segmentation identifying Class A products driving 80% of revenue
• Full DMAIC Six Sigma structured analysis - Define through Control
• Live: https://karan-supply-chain.streamlit.app
• Stack: Python · SQL · SQLite · Plotly · Streamlit · DMAIC

Same 180,519 order dataset rebuilt in Power BI - demonstrating Microsoft stack proficiency

• 4-page interactive report: Executive Summary, Delivery Performance, Revenue, ABC Inventory
• DAX measures for KPI calculations
• Designed for business stakeholders - not just technical audiences
• Stack: Power BI · DAX · DataCo Supply Chain Dataset

Standalone SQL showcase - 25 advanced queries across healthcare and supply chain datasets

• Basic through advanced SQL: window functions, CTEs, subqueries, running totals
• Cross-domain analysis: CMS Medicare + DataCo supply chain in same SQLite database
• RANK DENSE_RANK ROW_NUMBER LAG LEAD across real business datasets
• Streamlit dashboard showing queries alongside results
• Stack: SQL · SQLite · Python · Plotly · Streamlit

Predicting employee turnover to reduce hiring costs

• Analyzed 15,000+ employee records using Logistic Regression and Decision Trees
• Achieved 90% prediction accuracy - job satisfaction identified as top turnover driver
• Recommended strategies projected to reduce turnover by 20%
• Stack: R · Logistic Regression · Decision Trees · k-NN · SVM
• Repo: Human-Capital-Analysis

Loan default prediction reducing misclassification cost by $3M

• Built Logistic Regression and Decision Tree models on 5,960 loan applicants
• Improved sensitivity to 80.65%, reducing false negatives
• Demonstrated $3M cost reduction through optimized approval strategy
• Stack: R · Logistic Regression · Decision Trees
• Repo: Bank-Loan-Decision-Making-Analysis

Customer segmentation and brand loyalty prediction

• Segmented 600 consumer profiles using K-Means clustering
• Applied Random Forest and Logistic Regression for brand loyalty prediction
• Built for AXANTEUS market research agency
• Stack: R · K-Means · Random Forest · Logistic Regression
• Repo: Consumer-Segmentation-Analysis

Languages:        Python · R · SQL (basic through advanced window functions CTEs)
Visualization:    Plotly · Streamlit · Power BI · Tableau · Seaborn
ML/Analytics:     Scikit-learn · XGBoost · SHAP · Logistic Regression · Decision Trees
                  Random Forest · Clustering · Time Series · Predictive Modeling
Imbalance:        SMOTE (imbalanced-learn)
Database:         SQL · SQLite · PostgreSQL · MySQL · Excel (Advanced) · DAX
AI/LLM:           LangChain · OpenAI API · Hugging Face · ChromaDB RAG (coming soon)
Process:          Lean Six Sigma Black Belt · DMAIC · SIPOC · RCA · FMEA
Domain:           Healthcare · Supply Chain · HR Analytics · Finance · Recruitment

• Lean Six Sigma Black Belt - Benchmark Six Sigma (2021)
• Lean Six Sigma Green Belt - Benchmark Six Sigma (2021)
• MS Data Analytics - Webster University (Dec 2024) | GPA 3.31
• Google Data Analytics - Coursera (in progress)
• Microsoft PL-300 Power BI - Microsoft Learn (in progress)

Senior Accounts Manager - ID Medical LLP (Healthcare Staffing, UK) Managed data relationships with 30+ NHS hospitals · Improved forecasting accuracy 25% · 15% YoY revenue growth

Senior Recruitment Consultant - QX KPO Services 453 shifts booked in one month · £25,000 revenue · Led 4-member analytics team

International Peer Mentor & Writing Coach - Webster University CRLA Level 2 Certified · Improved student outcomes 94%

krntrivedi@gmail.com LinkedIn Healthcare Dashboard Supply Chain Dashboard ML Pipeline GitHub

12 projects in progress. One new deployment every 2 weeks. Check back soon.