Skip to content

ferpirro33/Marketing-ROI-Optimization

Repository files navigation

Project: TripleTen Data Analytics Business Project

Business Context

This project simulates a professional engagement within the Analytics Department of Showz, an event ticketing platform. The core challenge was to evaluate historical data to optimize marketing budgets and improve customer acquisition strategies.

🎯 Research Objectives

The analysis addresses critical business questions through a data-driven lens:

User Behavior: How do users interact with the platform across different devices?

Conversion Funnels: Identifying the exact touchpoints and time-to-conversion for first-time buyers.

Customer Lifetime Value (LTV): Quantifying the long-term financial contribution of each customer.

Profitability & Payback Period: Determining the exact point when revenue offsets Customer Acquisition Costs (CAC).

📊 Datasets Overview

Analysis of multi-source data spanning from January 2017 to December 2018:

Web Server Logs (Visits): Session-level data including Uid, device type, timestamps, and ad source IDs.

Transactional Data (Orders): Comprehensive record of purchases and revenue per user.

Marketing Spend (Expenses): Granular investment data categorized by acquisition source and date.

🛠️ Analytical Roadmap

Data Engineering & Preparation: Robust ETL process focusing on data type optimization and quality assurance.

Product Metrics: Calculated DAU, WAU, and MAU, session frequency, and ASL (Average Session Length) to determine retention rates.

Cohort Analysis: Segmented users by acquisition date to track conversion velocity, order volume, and average ticket size over time.

Marketing Performance (Unit Economics): * Calculated CAC (Customer Acquisition Cost) per source.

Modeled LTV (Lifetime Value) to understand long-term health.

Evaluated ROMI (Return on Marketing Investment) to identify the "break-even" point of various ad channels.

Data Visualization: Developed comparative dashboards to visualize performance trends across devices and advertising sources.

💡 Business Impact & Recommendations

The project concludes with a strategic roadmap for the marketing team. By identifying high-yield sources and inefficient channels, the analysis provides a data-backed recommendation on where to scale investment to maximize ROI and shorten the CAC payback period.

About

An end-to-end DA project focused on optimizing marketing spend for an e-commerce platform. This repository shows the full data lifecycle in several python libraries—from rigorous ETL and exploratory data analysis (EDA) to cohort analysis and ROMI modeling—providing actionable business insights to drive profitability.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors