Learning Engagement and Churn Analysis for an EdTech Platform

Overview

By analyzing engagement data across courses and cohorts, I identified key patterns that led to timely interventions and improved overall course completion rates.

Objectives

• Understand engagement behavior across learners and courses
• Identify churn drivers affecting course completion
• Optimize onboarding and engagement strategies using data insights
• Enable educators and teams to make data-backed content decisions

Approach

Data Collection & Modeling

• Collected multi-source engagement data (course progress, quiz scores, activity logs)
• Used SQL and Python to clean, transform, and model learner-level datasets

Exploratory & Diagnostic Analysis

• Conducted churn analysis to identify factors behind low completion rates
• Analyzed engagement frequency, quiz performance, and dropout timing
• Performed root cause analysis for behavioral and content-related churn drivers

Insights & Impact

• Students inactive for >7 days were 3× more likely to drop out
• Onboarding improvements and personalized nudges increased completion by 12%
• Redesigned reporting cut manual work by 40%

Collaboration & Implementation

Worked with content, product, and learning-experience teams; supported ongoing content optimization via KPI monitoring and automated updates.

Tech Stack

SQL · Python (Pandas, Matplotlib, NumPy) · Tableau · Excel

Outcome

Delivered actionable engagement insights that improved learner retention and enabled faster decision-making for educators.