MSc Business Analytics student at Aston University with a background in sales, commercial operations and data-driven decision support.

I am building a portfolio focused on SQL, Power BI, Python, business intelligence, machine learning and commercial analytics. My work combines practical business understanding with analytical tools to turn raw data into clear insights, dashboards and decision-ready recommendations.

• SQL-based business analysis
• Power BI dashboards and reporting
• Sales and commercial performance analytics
• Customer churn and retention analytics
• Revenue and profitability analysis
• Data quality checks and validation
• Business intelligence storytelling
• Python for data analysis and machine learning

Data and Analytics: SQL Server, Power BI, DAX, Python, Excel, Power Query Python and Machine Learning: Pandas, NumPy, Scikit-learn, Jupyter Notebook Business Analysis: KPI reporting, dashboard design, stakeholder reporting, churn analysis, revenue analysis, commercial insight generation Technical Areas: Data modelling, SQL views, data validation, trend analysis, segmentation, risk scoring, performance analysis Version Control: Git and GitHub

An end-to-end SQL Server and Power BI project using a synthetic UK commercial sales database.

The project covers database design, synthetic data generation, data quality checks, SQL business analysis, Power BI-ready reporting views and a seven-page interactive dashboard.

Key areas analysed:

• Revenue and profitability
• Monthly sales trends
• Regional and customer performance
• Product category performance
• Sales representative target achievement
• Returns and refund analysis
• Marketing campaign ROI

Project highlights:

• 300,000 orders
• 879,000 order-item records
• 20,000 customers
• 120 sales representatives
• 24,000 returns
• 100,000 marketing campaign responses
• £1.73bn total revenue analysed
• £247.75m gross profit analysed
• 104.2% revenue target achievement
• 90.8% of sales representatives above target

View the project here: SQL Commercial Sales Performance Analysis

An end-to-end churn analytics project using Python, SQL Server, machine learning and Power BI.

The project focuses on identifying churn drivers, estimating revenue at risk, predicting at-risk customers and translating model output into practical retention actions.

Key areas analysed:

• Overall churn and revenue at risk
• Churn by contract type
• Churn by tenure group
• Churn by payment method
• Churn by internet service
• Customer risk segmentation
• Model-based churn probability
• Recommended retention actions

Project highlights:

• 7,043 customers analysed
• 1,869 churned customers identified
• 26.5% overall churn rate
• £139,130.85 monthly revenue at risk
• £1.67m estimated annual revenue at risk
• Logistic Regression, Random Forest and Tuned Random Forest models compared
• Tuned Random Forest selected with 80.9% recall
• Customer risk bands created: Low, Medium, High and Critical Risk
• Five-page Power BI dashboard created for churn, revenue exposure and retention planning

View the project here: Customer Churn and Revenue Retention Analysis

I am currently developing projects that demonstrate practical analytics skills across:

• Business intelligence dashboards
• SQL portfolio projects
• Customer analytics
• Sales operations analytics
• Marketing and campaign performance analysis
• Predictive analytics using Python
• Machine learning for business decision-making

Before moving deeper into analytics, I built strong commercial experience across sales, FMCG, retail distribution and operational performance. This helps me approach data projects not only from a technical angle, but also from a business decision-making perspective.

My goal is to build analytics solutions that are clear, practical and useful for real business users.

LinkedIn: Chetan Singh GitHub: chetansinghanalytics