🧠 Quantium Data Analytics Virtual Experience – Forage

A data analytics project completed as part of the Quantium Job Simulation on Forage. This simulation mimics real-world retail challenges and demonstrates how data-driven insights can support customer segmentation, product strategy and store performance evaluation.

This experience involved analyzing retail transaction and customer data to deliver insights in three core areas:

1. 🧾 Customer Behavior Analysis
2. 📈 Trial vs Control Store Performance Evaluation
3. 📊 Data Storytelling & Reporting

📌 Project Overview

The objective of this simulation was to analyze snacking chips customer data, evaluate a trial store layout intervention and provide actionable insights for Quantium’s retail client.

📂 Project Breakdown

Task 1: 🧾 Customer & Sales Analysis

Objective: Understand customer purchasing behavior and identify key segments.

Steps:

• Analyzed transaction and customer datasets
• Cleaned and joined transaction and customer datasets
• Analyzed chip units sold and sales by identified customer segments
• Created visualizations to explore behavioral trends

Results:

• Identified Mainstream Young Singles & Couples as primary category shoppers
• Found growth potential among Young and Older Families
• Observed consistent affluence across life stages but higher engagement from family groups

Files:

• Dataset Files: QVI_purchase_behaviour, QVI_transaction_data
• Code File: Data Exploration and Analysis - Task 1.Rmd
• Code with Output/Results File: Data Exploration and Analysis - Task 1.pdf

Task 2: 🧪 Trial vs Control Store Analysis

Objective: Find control stores based on the prior performance of the trial stores

Steps:

• Defined performance metrics (e.g., total sales, number of customers)
• Selected Control Stores based on trend similarity (not averages)
• Conducted comparative time series analysis
• Used ggplot2 to visualize trends pre and post-trial

Results:

• Identified control stores for the trial stores
• Delivered recommendations based on sales lift and engagement patterns

Files:

• Dataset File (Created after running code in Task 1): QVI_data.csv
• Code File: Retail Strategy and Analytics - Task 2.Rmd
• Code with Output/Results File: Retail Strategy and Analytics - Task 2.pdf

Task 3: 📊 Insights & Reporting

Objective: Structure insights using the Pyramid Principle and present to stakeholders.

Steps:

• Synthesized findings into a business-focused narrative
• Created polished data visualizations and slide summaries
• Compiled a report with recommendations and key takeaways

Results:

• Final report (R Markdown to PDF)
• Slide-ready visuals
• Strategic insights for scaling the layout intervention across stores

Files:

• PowerPoint Presentation: Presentation_BRAND - Task 3.pptx

• File for client: Presentation_BRAND - Task 3.pdf

  📊 Technologies Used:

• R (dplyr, tidyr, ggplot2, ggmosaic, lubridate, scale, )

• RMarkdown for reproducible reporting

• PowerPoint for stakeholder communication

• PDF for creating final files and reports

📈 Business Impact:

• Data supports scaling the layout redesign to stores with similar profiles

• Customer segmentation enables more targeted promotions

• Insights help optimize store experience and chip category performance

  👤 Author

Siddharth Gada
📧 Email: gadasiddharth@gmail.com
🔗 LinkedIn: https://www.linkedin.com/in/siddharthgada/