How volkan35koc/supermarket-sales-and-profitability-performance-analysis works
This repository is a supermarket performance analysis project, not a software service. Its documented workflow uses Superstore.csv in a Jupyter notebook for data preparation and exploratory analysis, then applies a Random Forest regressor to predict profit and evaluates it with MAE. The README also reports findings on yearly performance, loss-making furniture subcategories, and discount-related losses. No notebook source was provided, so the graph reflects documented capabilities and relationships only; component paths identify the notebook or dataset, not inspected implementation details.
Main entry points: superstore.ipynb Data preparation · Superstore.csv Superstore sales
Components 10
Data
- Superstore sales
Superstore.csv
Exploratory analysis
- Analysis notebook
superstore.ipynb - Data preparation
superstore.ipynb - Time trends
superstore.ipynb - Category profitability
superstore.ipynb - Discount analysis
superstore.ipynb - Business findings
superstore.ipynb
Profit prediction
- Random Forest
superstore.ipynb - MAE evaluation
superstore.ipynb
Other components
- Analyst
Connections 11
- Analyst → Analysis notebook: runs
README.md - Superstore sales → Data preparation: provides data
README.md - Analysis notebook → Data preparation: performs
README.md - Data preparation → Time trends: enables
README.md - Data preparation → Category profitability: enables
README.md - Data preparation → Discount analysis: enables
README.md - Time trends → Business findings: identifies trends
README.md - Category profitability → Business findings: identifies losses
README.md - Discount analysis → Business findings: reveals impact
README.md - Data preparation → Random Forest: supplies features
README.md - Random Forest → MAE evaluation: evaluated by
README.md