Final-year student · Data Analytics · Finance · Healthcare · Consulting
- 📊 Final-year student with a biotech mind and a data analyst's toolkit — 10 shipped projects across finance, healthcare, and consulting analytics, 900K+ records analysed
- 🎓 B.Tech Biotechnology, Amity University — domain knowledge in life sciences that gives me an edge in healthcare and R&D analytics
- 🏥 Currently a Research Intern at IIT (ISM) Dhanbad (SRIS 2026)
- 🔬 2+ years in the Systems Biology & Data Analytics Lab, Amity Institute of Biotechnology
- 🤖 Building end-to-end analytics — warehouses, risk models, forecasting, and RAG/GenAI tools — not just notebooks
- 💼 Targeting roles in financial services, healthcare analytics, and management consulting
- 📫 Reach me at akansha0724@gmail.com
Business thinking → I frame problems as decisions, not just models
Domain knowledge → Biology + healthcare gives me an edge in life sciences analytics
Technical depth → End-to-end pipelines from raw data to actionable insight
Communication → Translating complex analysis into clear business recommendations
Analytics & Data
ML & Insights
Reporting, GenAI & Deployment
| Project | Problem | Outcome |
|---|---|---|
| 📈 Mutual Fund Analytics Warehouse | End-to-end MySQL star-schema warehouse over 100K+ rows of AMFI-style fund data — ETL, data-quality gates, Excel dashboard | 102 automated tests, 58 data-quality checks, all passing · Direct plans cost 0.78% vs 1.35% Regular TER · MySQL, Python ETL, pytest |
| 💳 Credit Default Risk Analytics | Predict credit-card default on 30K real clients and turn the model into a cost-optimal approve/decline decision — the core job at a card issuer | PR-AUC 0.56 vs 0.22 baseline, cost-based threshold cuts expected loss 26%, catches 75% of defaulters · SHAP-explained · MySQL, scikit-learn, SHAP |
| 🩺 30-Day Readmission Risk Model | Predict 30-day hospital readmission on 101,766 real patient encounters — SQL cohort analysis, hypothesis testing, risk ranking | ROC-AUC 0.64, top 30% of patients captures 48% of all readmissions · MySQL, Python, scikit-learn |
| 💬 FundGPT — RAG over Fund Factsheets | Retrieval-augmented Q&A over 40 fund factsheets generated from the warehouse above — "which fund has the lowest expense ratio?" gets a cited answer | 100% retrieval hit-rate@1 on a 20-question eval · zero-cost structured answer engine + optional Claude synthesis |
| 🔍 Healthcare Claims FWA — Payer Audit Prioritization | Rank 200+ NY hospitals by billing-outlier risk across 111,155 real claims lines and screen the provider network against the 83,464-entry federal exclusion list — the payment-integrity workflow at Optum, a Blue plan, or CMS | 6 of 200 facilities flagged by both a peer-benchmark detector and Isolation Forest · 83K-provider OIG exclusion screen · MySQL, scikit-learn |
| Project | Problem | Outcome |
|---|---|---|
| 🏥 Hospital Readmissions Risk Analysis | Analyse 64K CMS records across 4,239 hospitals — identify which conditions, states, and hospitals drive 30-day readmission risk | 15-pt protocol gap (16.3%–31.3%) on heart failure readmissions, hospital size shown to have negligible effect · MySQL · Python · Excel dashboard |
| 📉 Equity Settlement Risk Analysis | Analyse 507K real SEC settlement failure records — identify where operational risk concentrates and when stress events occur | $147B March stress event identified, ETF concentration risk, chronic vs spike classification · MySQL · Python · Excel |
| 💊 Medical Cost Forecasting | Forecast 10-year US healthcare spending across 6 CMS service lines, benchmarking Prophet vs ARIMA vs Holt-Winters | No single model dominates — Prophet wins on stable series, ARIMA on COVID-disrupted lines, Holt-Winters on slow-moving series · MySQL · Python · Excel |
| 🍄 Fungal Pathogenicity Predictor | Classify fungal disease risk across 9 pathogen types from trait data — relevant to pharma R&D and agricultural risk | 92.2% accuracy, SHAP-driven feature insights, production-ready sklearn pipeline |
| 📊 Student Performance Predictor | Predict academic outcomes and surface early intervention signals | Flask dashboard with SSI scoring and recommendations |
- 📈 Financial Analytics — risk modelling, portfolio analysis, business performance dashboards
- 🏥 Healthcare Analytics — patient outcomes, operational efficiency, clinical trial data
- 🧩 Consulting Analytics — market analysis, KPI frameworks, data-driven strategy
- 🤖 GenAI in Analytics — RAG systems, LLM-powered reporting, automated insight generation
Open to data analyst roles in finance, healthcare, and consulting — see the full portfolio for the details.