Disclaimer
I cannot share or use the proprietary data I worked with at my current place of employment. To demonstrate similar skills and workflows, I built parallel projects using publicly available open-source datasets.
📈 Growth marketing traffic OPTIMIZATION:
​
🎯 Business Problem
Marketing spend was rising, but conversions remained flat, raising concerns about wasted budget and inefficient traffic sources. The business lacked a clear, data-driven framework to identify which channels to scale, optimize, or cut.
​
Marketing efficiency linked to:
ROAS (Return on Ad Spend), Blended CPA (Cost per Acquisition), Conversion Rate, Customer Base Growth, Average Order Value
👤 Customer Segmentation & Analytics:
​
🎯 Business Problem
The business lacked a structured view of its customer base. Without clear segmentation, it was difficult to:
-
Prioritize high-value customers
-
Detect at-risk or churned users
-
Tailor marketing campaigns to different customer types
-
Understand how engagement and revenue trends evolve over time
-
Make informed decisions about pricing, product features, and retention investments
This led to inefficient marketing spend, missed upsell opportunities, and low visibility into customer health.
​
Customer analytics linked to:
-
Retention, Marketing ROI, CLTV, Personalization, Churn reduction, Engagement, AOV, and Customer quality.
​
📦 Delivery Performance OPTIMIZATION:
Customer Satisfaction, Product Categories, and Customer States
​
🎯 Business Problem
The core business objective is to increase customer satisfaction and experience.
Since a significant portion of customer dissatisfaction stems from poor delivery experiences,
the delivery system was chosen as the main area for operational investigation and improvement.
​
Customer satisfaction linked to:
CLTV, Churn, AOV, Repeat purchase