Skip to content

Acelake123/Forage_Quantium_Data_Analytics

Repository files navigation

Forage      Quantium

🛒 Quantium Data Analytics Job Simulation

Powered by Forage · End-to-End Retail Analytics


Python Jupyter Power BI Excel


A hands-on virtual internship exploring retail transaction data through customer segmentation, uplift testing, and strategic commercial insights — the way Quantium's data teams actually work.



📌 About This Project

This repository contains all deliverables from the Quantium Data Analytics Virtual Job Simulation hosted on Forage. The simulation mirrors real-world analytics workflows at Quantium — one of Australia's leading data science and analytics firms — spanning data wrangling, statistical experimentation, and executive storytelling.



🗂️ Repository Structure

📦 Forage_Quantium_Data_Analytics
 ┣ 📁 Task 1: Data Preparation and Customer Analytics
 ┃   ┣ 📓 Jupyter Notebook (.ipynb)
 ┃   ┗ 📊 Power BI Report (.pdf)
 ┣ 📁 Task 2: Experimenting and Uplift Testing
 ┃   ┗ 📓 Jupyter Notebook (.ipynb)
 ┣ 📁 Task 3: Analytics and Commercial Application
 ┃   ┗ 📊 Presentation (.pptx)
 ┗ 🏅 Completion Certificate (.pdf)


🚀 Tasks Overview


🧹 Task 1 — Data Cleaning & Customer Analytics

"Understand the who behind the what."

Dived deep into Quantium's retail transaction dataset to uncover who is buying chips and why. Performed rigorous data cleaning, feature engineering, and customer segmentation to identify high-value customer groups and their purchasing behaviours.

Key Highlights:

  • 🔍 Cleaned and standardized raw transaction & customer data
  • 👥 Segmented customers by lifestage and premium tier
  • 📈 Identified top-performing customer segments by sales contribution
  • 📊 Visualized insights in Power BI for stakeholder reporting
Deliverable Link
📓 Python Jupyter Notebook Open in nbviewer →
📊 Power BI Analysis PDF View Report →


🧪 Task 2 — Experimenting & Uplift Testing

"Did the trial stores actually make a difference?"

Applied control store methodology to evaluate the performance of trial store layouts. Used statistical techniques to identify the best-matched control stores and measure incremental sales uplift with confidence.

Key Highlights:

  • 🏪 Matched trial stores to statistically similar control stores
  • 📉 Conducted pre/post performance comparisons
  • 📐 Applied Pearson correlation & magnitude distance scoring
  • ✅ Validated uplift significance using hypothesis testing
Deliverable Link
📓 Python Jupyter Notebook Open in nbviewer →


📣 Task 3 — Analytics & Commercial Applications

"Translate numbers into a story the boardroom actually cares about."

Synthesized insights from Tasks 1 & 2 into a polished executive presentation tailored for the Category Manager. Communicated findings in a clear, data-backed narrative with actionable commercial recommendations.

Key Highlights:

  • 🗣️ Built a compelling story around the data insights
  • 💼 Aligned recommendations with business objectives
  • 🎨 Designed a professional slide deck using the Quantium template
  • 📌 Prioritised actionable next steps for the client
Deliverable Link
📊 PowerPoint Presentation View Slides →


🛠️ Tech Stack

Tool Purpose
Python (pandas, matplotlib, scipy) Data wrangling, EDA, statistical testing
Jupyter Notebook Interactive analysis & documentation
Power BI Customer analytics dashboard
Microsoft PowerPoint Executive presentation
Excel Supplementary data handling


🏅 Completion Certificate

Successfully completed all three tasks and earned the official Quantium Data Analytics Job Simulation Certificate from Forage.

Certificate



Built with 📊 data, ☕ coffee, and a passion for turning raw numbers into real decisions.

If this project helped you, consider starring the repo!

About

This repository serves as a comprehensive archive of my work from the Quantium Data Analytics Job Simulation hosted by Forage. It includes all project deliverables across Jupyter Notebooks, Power BI, Excel, and PDF formats.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors