Mobile Game Analytics

Exploratory data analysis, A/B testing, and predictive modeling for a mobile game.
The project covers KPI tracking, experiment evaluation, and machine learning modeling to understand player behavior and monetization patterns.

---

📊 Project Overview

This project is divided into three main parts:

1. Exploratory Data Analysis (EDA)

   • Cohorted and daily KPIs:
     • Daily Active Users (DAU)
     • Average Revenue Per User (ARPU)
     • Average Revenue Per Daily Active User (ARPDAU)
     • Retention rates
     • Return on Ad Spend (ROAS)
   • Key findings, positive and negative trends, and action suggestions.

2. A/B Testing

   • Evaluation of two experimental groups using:
     • Monetization metrics
     • Engagement metrics
   • Statistical tests to decide which variant performs better.

3. Predictive Modeling

   • Objective: Predict whether a user will make a purchase within 30 days based on their first 7 days of activity.
   • Includes:
     • Data preparation & cleaning
     • Feature engineering
     • Model selection & training
     • Model evaluation & validation

---

⚙️ Tech Stack

• Languages: SQL, Python
• Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn, statsmodels
• Tools: Jupyter Notebook / VS Code

---