01
Healthcare Analytics
Patient-risk identification, preventive cost reduction, demand forecasting, and hospital resource optimization.
Data · Machine Learning · Strategic Decision Support
Using data to solve high-impact problems in healthcare, finance, and business.
My work demonstrates how predictive analytics, machine learning, and business intelligence can help organizations identify risk earlier, forecast future outcomes, allocate resources more effectively, and make stronger financial and operational decisions.
The common thread across every project is simple: turn complex data into an action that creates measurable value.
Three professional pillars
One analytical approach applied to different industries.
Data science becomes valuable when it is connected to a decision, a stakeholder, and a measurable outcome.
02
Financial Analytics
Financial modeling, SEC filing text analysis, market-signal evaluation, forecasting, and evidence-based investment interpretation.
03
Machine Learning for Business
Classification, regression, forecasting, ranking, validation, explainability, and optimization across complex organizational problems.
What data can help organizations do
Predict, prioritize, optimize, and communicate.
Selected evidence
Real results from healthcare and financial analytics projects.
Data and model gallery
Visual evidence supporting the project stories.
The charts below illustrate model performance, feature influence, forecasting results, and how analytical workflows connect to decisions.
Healthcare Risk Classification
Model comparison helps determine which approach best balances sensitivity, precision, and practical healthcare value.
Future Healthcare Cost Risk
Ranking performance shows how predictive analytics can concentrate preventive resources among the highest-risk patients.
Hospital Demand Forecasting
Comparing forecasting methods supports a more defensible choice for staffing and capacity planning.
Financial NLP and Market Prediction
Financial-only, text-only, and combined models test whether SEC filing language adds useful predictive information.
Financial Feature Interpretation
Coefficient analysis helps explain which numerical and textual variables contribute most strongly to the model.
From Data to Action
Every project follows a disciplined path from business understanding to validation and strategic decision support.
Cross-industry applications
Machine learning can support almost any organization with data and decisions.
Healthcare
Risk prediction, cost prevention, demand forecasting, patient segmentation, and resource allocation.
Finance
Market signals, risk analysis, forecasting, fraud detection, credit scoring, and investment research.
Operations
Capacity planning, staffing, scheduling, inventory, maintenance, and process optimization.
Business Intelligence
Dashboards, KPI monitoring, trend analysis, executive reporting, and strategic planning.
Marketing
Customer segmentation, churn prediction, campaign measurement, and lifetime-value analysis.
Risk & Compliance
Anomaly detection, scenario analysis, model governance, and evidence-based oversight.
Public Sector
Resource targeting, program evaluation, demand forecasting, and community-level decision support.
Real Estate
Portfolio performance, occupancy, pricing, operating trends, and asset-management insights.
Healthcare and finance together
Two sectors where better predictions can change lives and protect value.
Feedback and quality
Recognized for technical depth, organization, and business relevance.
The statements below summarize recurring academic and project feedback themes and are not presented as direct endorsements by named individuals.
Strong command of the complete analytics process, including data preparation, model comparison, validation, and actionable recommendations.
Clear attention to meaningful metrics, model limitations, and the practical consequences of analytical decisions.
Professional communication that makes complex analytical findings understandable to business and healthcare decision-makers.
Data-driven collaboration
Let’s turn complex data into decisions that create meaningful value.
Whether the challenge involves healthcare, finance, operations, risk, or business intelligence, the analytical process remains the same: understand the problem, build evidence, validate the model, and translate results into action.