The company has recently launched a new sign-up experience but lacks visibility into funnel performance and user experience. Analyze the user funnel, identify where and why users are dropping off, and provide recommendations to improve conversion and activation rate.
In this project, I analyzed key funnel metrics including conversion rate, drop-off rate, and activation rate to evaluate the performance of the new sign-up experience. I identified specific stages in the funnel where users were dropping off, signaling friction points in the user journey. To enrich the analysis, I engineered new variables such as time of day and day of week, and leveraged existing data on acquisition channels to perform cohort analysis. This allowed me to uncover nuanced behavior patterns across different user segments and provide targeted, data-driven recommendations.
The major drop-off points in the funnel occur after email submission (21.2% drop-off) and then when setting password and starting the trial (29.5% and 26.7% respectively). In between submitting contact info and setting the password there was negligible drop-off between these steps. For each of the three key friction points, I developed two targeted A/B testing ideas, along with additional actionable product recommendations to enhance the sign-up flow. My data-driven insights and structured experimentation approach were well-received, and the clarity of my recommendations left a strong impression on the team.
Case_Study.csv, a funnel activities dataset with columns: user_id, timestamp, step-completed, and channel. The data ranges from 03-01-2025 to 03-31-2025.
Funnel_slide_deck.pdf, a presentation with includes summary of key insights, visualizations, and actionable recommendations.
A jupyter notebook, a working file with SQL queries to locally processing the data, calculate KPIs, and conduct segment analysis.
The data is kindly provided by a fintech company.