All Work
Automobile · KPI Architecture
Car Sales Multi-Axis Analysis
End-to-end car sales analysis using Python, SQL, and Power BI — from messy raw files to KPI dashboards and seasonal demand insight.
PythonSQLPower BI
- DATA↓
- CLEAN↓
- ANALYZE↓
- VISUALIZE↓
- INSIGHT↓
- ACTION
Business Problem
Sales data was fragmented across files and reports, making it hard to see performance clearly across channels, regions, and time.
Objective
Build a multi-axis analytics workflow that cleans sales data, models KPIs, and surfaces seasonal demand patterns decision-makers can act on.
Dataset
Automobile sales records spanning channels, regions, product lines, and time periods.
Tech Stack
Python, SQL, Power BI
Data Preparation
- Standardized product, region, and channel fields
- Handled missing and inconsistent sales records
- Prepared analysis-ready tables for SQL and Power BI
Analysis Process
- SQL queries for performance by region, channel, and product
- Python exploratory analysis and time-series pattern checks
- Custom KPI architecture in Power BI
- Automated ETL steps to reduce manual cleaning latency
Key Insights
- Seasonal demand patterns became visible through time-series forecasting
- Multi-axis KPI views improved sales visibility across key dimensions
- Automated preparation reduced repeated manual cleaning work
Business Recommendations
- Track the defined KPI set continuously instead of ad-hoc spreadsheets
- Use seasonal demand windows to plan inventory and promotions
- Keep ETL refresh automated so reporting stays current
Outcome
See full case study for process detail and deliverables.
Next Project
Healthcare Patient Analytics