Design Push-Notification System for Airport Surge Pricing
Overview
This question evaluates a data scientist's competency in designing ML-driven real-time decision systems, covering feature engineering, predictive modeling for supply–demand imbalance, budgeted ranking for notifications, and operational constraints like per-driver throttling; it is categorized under Machine Learning for a Data Scientist role.
Upstart
Aug 4, 2025, 10:55 AM
Data Scientist
Technical Screen
Machine Learning
40
0
Designing Airport Surge Push Notifications for Drivers
Context
You are building a real-time system for a ride-hailing platform. When an airport experiences a surge (passenger demand exceeds available drivers), the system should decide:
- How many drivers to notify (the "budget").
- Which specific drivers to notify (the "ranking").
Assume you have real-time telemetry for drivers, trips, and demand forecasts, and you can send push notifications with per-driver throttling.
Task
- Outline a system to determine how many drivers to target and which drivers to include when airport surge pricing occurs.
- Explain why a simple distance-radius rule (e.g., notify anyone within 10 miles) can perform poorly, and propose improvements.
- Besides ETA, list additional features/metrics you would engineer to decide whether to send a notification.
- If neighborhood-level supply–demand imbalance is predictive, describe how you would detect whether a region is imbalanced enough to trigger a notification.
Hints
- Discuss feature engineering, predictive modeling, supply–demand signals, real-time data, and model evaluation.
Solution
Login required
Show