Retail Demand Forecasting and Price Elasticity Analytics

Internship repository for the Python Data Science / Machine Learning assignment assigned to GitHub user zaidnayaz.

Project Overview

This project is the foundation for an enterprise-grade demand forecasting and price elasticity analytics platform for a multi-store retail organization. The platform is planned to ingest sales data, clean and validate records, generate daily/weekly/monthly sales features, and later support forecasting, price elasticity analysis, dashboards, APIs, and deployment.

Internship Progress

Current status: Day 1 to Day 6 completed.

Month 1 goal from the assignment: build the data pipeline, database structure, and basic analytics dashboard foundation.

Day	Focus Area	Work Completed	Output
Day 1	Orientation and project setup	Reviewed internship expectations, created repository structure, planned Python environment, and documented project scope.	README.md, .gitignore, requirements.txt, docs/project_plan.md
Day 2	Architecture and database planning	Designed initial system layers and PostgreSQL-ready schema for stores, products, customers, promotions, inventory, and sales transactions.	docs/architecture.md, sql/schema.sql
Day 3	GitHub repository management	Organized folders for daily logs, source code, SQL, data samples, reports, and documentation. Prepared daily learning logs for manager review.	Daily_Log/, repository structure
Day 4	Data ingestion	Added sample retail datasets and a reusable CSV ingestion module.	data/sample/, src/etl/ingest.py
Day 5	Data cleaning and validation	Added checks for missing values, duplicate records, invalid quantities, invalid prices, and date parsing.	src/etl/ingest.py
Day 6	Feature engineering and reporting	Created sales features for revenue, daily sales, weekly sales, monthly sales, product-wise sales, store-wise sales, and category-wise sales.	src/features/sales_features.py, src/reports/sales_summary.py

What I Learned

• How an industry internship is evaluated through consistent delivery, documentation, GitHub activity, and professional communication.
• Why software projects need planning before coding, including architecture, database design, and UI/UX thinking.
• How GitHub acts as a daily learning tracker, assignment record, and professional portfolio.
• How month-1 data science project work starts with clean structure, reliable data ingestion, validation, and repeatable reporting.

Repository Structure

.
|-- Daily_Log/
|-- data/
|   `-- sample/
|-- docs/
|-- outputs/
|   `-- reports/
|-- scripts/
|-- sql/
|-- src/
|   |-- etl/
|   |-- features/
|   `-- reports/
|-- .env.example
|-- .gitignore
|-- README.md
`-- requirements.txt

How to Run the Day 6 Summary

1. Create and activate a Python virtual environment.
2. Install dependencies:

pip install -r requirements.txt

3. Run the summary script:

python -m src.reports.sales_summary

4. Review the generated report:

outputs/reports/day_06_sales_summary.csv

Month 1 Roadmap

• Complete PostgreSQL database implementation.
• Expand ETL validation and automated cleaning.
• Add SQL analysis using joins, grouping, window functions, CTEs, and indexes.
• Build an initial analytics dashboard for sales overview, product performance, store performance, revenue summary, and top selling products.
• Maintain GitHub updates and daily learning logs.

Source Material Used

• Internship assignment PDF: Python Data Science / Machine Learning project guide.
• Presentation 1: Building Industry-Ready Software Professionals.
• Presentation 2: GitHub Repository Management for Students.
• Presentation 3: Project Architecture, Database Design and UI/UX Planning.