Build a predictive model from TurboTax sample data
Company: Intuit
Role: Data Scientist
Category: Machine Learning
Difficulty: easy
Interview Round: Onsite
You receive a **TurboTax sample dataset** (user-level and/or session-level) and are asked to build a predictive model.
## Task
1. Pick a concrete prediction target (choose one and justify):
- Probability a user will **file** within 14 days of starting.
- Probability a user will **churn** (not file this season).
- Expected **revenue** from the user this season.
2. Describe how you would:
- Define labels and avoid label leakage.
- Build features from product interactions and historical attributes.
- Choose a baseline model and at least one stronger model.
- Evaluate performance (metrics, calibration, slice performance).
- Turn the model into an actionable recommendation (e.g., targeting, prioritization, interventions).
## Constraints / realism
- Data may be missing or delayed.
- Class imbalance is likely (e.g., churn).
- The business cares about interpretability and safe deployment.
Quick Answer: This question evaluates predictive modeling skills including target selection, label leakage prevention, feature engineering from product and historical interaction data, model selection and evaluation, and considerations for deployment and interpretability using a tax-preparation sample dataset.