Predict Robinhood Churn | Dataford Interview Questions

Tell me about how you would predict churn for Robinhood users.

Use the provided users and user_activity tables to produce a reproducible SQL-based churn-risk output as of March 31, 2025. Consider users created by the cutoff who have at least one recorded activity, and classify users based on days since their latest activity.

Output

One row per included user with user_id, email, last_activity_date, days_since_last_activity, total_activities, trade_count, and churn_risk
Exclude users with no activity and users created after the cutoff
Order by risk from highest to lowest, then by user_id ascending

Schema

users

Column	Type	Description
user_idPK	INT	Unique Robinhood user identifier
email	VARCHAR(255)	User email address
created_at	DATE	Date the user account was created

user_activity

Column	Type	Description
activity_idPK	INT	Unique activity identifier
user_id	INT	User associated with the activity
activity_date	DATE	Date the activity occurred
activity_type	VARCHAR(30)	Activity category, such as login or trade

Your question is Predict Robinhood Churn. Start with the requirements and the two tables in the Question tab.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.

Problem