CrackML by @ml.with.umang
Interview questions / ML System Design
ML System Design interview question

Design a Traffic-Data ML System

Design a scalable ML system that predicts a traffic-related target from streaming and historical road data.

hardsystem designEvidence 77/1001 source reportGoogle

The 60-second answer

Clarify the target—ETA, congestion, incidents, or route cost—and define horizon, freshness, geography, and downstream decision impact. Build event-time ingestion with map matching, deduplication, late-data handling, road topology, recent speeds, historical seasonality, weather/events, and neighboring-segment context.

Build the answer in this order

1
Frame the problem

Clarify the target—ETA, congestion, incidents, or route cost—and define horizon, freshness, geography, and downstream decision impact.

2
Design the data path

Build event-time ingestion with map matching, deduplication, late-data handling, road topology, recent speeds, historical seasonality, weather/events, and neighboring-segment context.

3
Choose the modeling stack

Start with a strong baseline and add sequence/graph models only when time/geography backtests show meaningful gain.

4
Serve, evaluate, iterate

Serve fresh features with historical fallbacks and monitor regional drift, sensor coverage, calibration, latency, and routing impact.

A useful interview mental model

This is the shape of a strong answer—not a script to memorize.

01Requirements
02Data
03Model / Retrieval
04Serving
05Monitor

Senior-level signal

  • Senior answers address graph dependencies, delayed/biased observations, regional cold start, and online/offline feature parity.
  • Discuss how prediction uncertainty should change routing or fallback behavior.

What the interviewer is really testing

Product framing, data design, modeling choices, serving constraints, reliability, evaluation, and explicit trade-offs.

Likely follow-up questions

What changes at 10× traffic or data volume?
Which failure mode would you monitor first in production?
How would you evaluate this offline and online before rollout?

Common weak-answer patterns

  • Jumping to a model before defining the product contract.
  • Listing components without bottlenecks, metrics, or failure handling.
  • Ignoring data quality, serving latency, monitoring, and iteration.