Data & Analytics Professional with 9+ years of experience in enterprise analytics, business intelligence, procurement analytics, and data-driven decision making at HSBC.

Currently focused on:

• Machine Learning
• MLOps & Model Deployment
• Predictive Analytics
• AI/LLM Applications
• Data Science Portfolio Projects

I enjoy building end-to-end ML systems — from exploratory data analysis to deployment-ready applications.

• 9+ years of experience in analytics and reporting within enterprise banking environments
• Strong background in:
  • Business Intelligence
  • Data Analytics
  • KPI Reporting
  • Dashboard Development
  • Stakeholder Management
  • Process Optimization
• Transitioning into advanced Machine Learning and MLOps engineering
• Passionate about solving business problems using data and AI

• Python
• SQL
• Pandas
• NumPy
• Scikit-learn
• Matplotlib
• Seaborn

• Regression
• Classification
• Model Evaluation
• Feature Engineering
• Hyperparameter Tuning

• FastAPI
• Docker
• Git & GitHub
• CI/CD Concepts
• Model Packaging
• API Deployment

• Tableau
• Power BI
• Excel
• Data Visualization
• Business Reporting
• KPI Analytics

End-to-end Machine Learning project that predicts insurance premiums using customer health and demographic data.

• Performed Exploratory Data Analysis (EDA)
• Conducted Hypothesis Testing
• Built Regression Models
• Feature Engineering using BMI and health indicators
• Model evaluation using R² and error metrics
• Business-focused storytelling and insights

Python | Pandas | Scikit-learn | Matplotlib | Seaborn

Premium costs increase disproportionately with age and health risk factors, demonstrating nonlinear risk amplification patterns.

Production-style Machine Learning pipeline for customer churn prediction with deployment-focused architecture.

• Built modular ML pipeline
• Implemented model training and inference workflow
• API development using FastAPI
• Docker containerization
• GitHub version control integration
• Deployment-ready structure

Python | FastAPI | Docker | Scikit-learn | GitHub

• Reproducibility
• Scalability
• Deployment readiness
• Production-oriented ML workflows

Worked across enterprise analytics and reporting functions supporting business operations and decision-making.

Key contributions include:

• Built analytical reports and dashboards for stakeholders
• Automated recurring reporting workflows
• Improved reporting efficiency and data accuracy
• Worked with large enterprise datasets
• Supported strategic business decisions through analytics
• Delivered KPI tracking and operational insights

• Advanced Machine Learning
• MLOps
• LLM & Prompt Engineering
• AI Applications in Analytics
• Cloud Deployment
• Data Engineering Fundamentals

• LinkedIn: www.linkedin.com/in/pavanlanka
• GitHub: https://github.com/Pavan202020

To combine enterprise analytics experience with modern Machine Learning and MLOps practices to build scalable AI-driven business solutions.