Your learning path

Data Science & Machine Learning

Build the foundations, choose a specialization, then apply it to real problems.

Interview Lab

How each interview works

  1. 01
    Read the repositoryTrace the contract before changing code.
  2. 02
    Make a focused changeRepair, complete, extend, or test one behavior.
  3. 03
    Explain the decisionDefend edge cases, trade-offs, and complexity.
Progressive interview curriculum

Each repository prepares the next one.

Follow the path in order, or enter at the stage that matches your interview.

Practice formats
01ReadTrace and explain
02DebugDiagnose and repair
03CompleteFinish focused gaps
04ExtendAdapt a working core
I

Python and pairing foundations

Learn to read an unfamiliar contract, preserve grid state, review classifier decisions, and finish with a first leakage-safe evaluation.

II

Probability, statistics, and experiments

Build trustworthy decisions from classifier metrics, controlled experiments, uncertainty, and calibrated probabilities.

III

Modeling and product decisions

Apply evaluation skills to recommendation ranking, causal retention questions, and a leakage-free offline validation.

IV

Production ML and AI systems

Move from a stable serving boundary to auditable risk decisions, grounded retrieval, and inference memory.

Bonus exercises

Test the reasoning behind reliable code.

Check probability intuition with a simulation, repair tests that make incorrect claims about working code, and recommend to a member the system has never seen.

Bonus 01Complete

Monty Hall: Stay or Switch?

Complete a reproducible simulation, preserve the host’s information rule, and connect the observed win rates to conditional probability.

Conditional probabilitySimulation
40 min
Bonus 02Test repair

Repair the Model Ranking Tests

Repair three incorrect pytest expectations, then prove the corrected tests detect broken ranking implementations.

pytestTest debugging
35 min
Bonus 03Complete

Cold-Start Picks

Recommend movies to a brand-new member from a user–movie rating matrix, handling the unrated (None) entries that make the new member cold.

Collaborative filteringCosine similarity
45 min