AIML Rounds

QUIZ

ML core concepts

10 questions on ML core concepts, from 7 lessons. Pick an answer in your head, then open it.

On the roadmap for: AI Engineering, ML Engineering, Data Science.

  1. Question 1 of 10

    Your model has high error on both training and validation data. What is the most likely issue?

    1. A. Data leakage between training and validation
    2. B. High variance: the model is overfitting the training data
    3. C. Too much training data for the model's size
    4. D. High bias: the model is too simple to fit the data
    View answer

    ✓ D. High bias: the model is too simple to fit the data

    If it can't even fit the training data, add capacity or better features, not more data.

    Lesson: The Bias–Variance Trade-off

  2. Question 2 of 10

    Training error is low but validation error is much higher. Which fix fits?

    1. A. Add regularisation or more training data
    2. B. Train for more epochs until validation improves
    3. C. Remove the validation set and train on everything
    4. D. Make the model bigger so it can fit better
    View answer

    ✓ A. Add regularisation or more training data

    A big gap between train and validation is variance. Regularisation, more data or a simpler model reduce it.

    Lesson: The Bias–Variance Trade-off

  3. Question 3 of 10

    Which of these causes data leakage?

    1. A. Keeping a separate held-out test set untouched until the end
    2. B. Splitting into folds first, then fitting the scaler inside each one
    3. C. Shuffling the training rows before each epoch so batches differ every time
    4. D. Fitting the scaler or picking features on all data before cross-validation
    View answer

    ✓ D. Fitting the scaler or picking features on all data before cross-validation

    Preprocessing must be fitted inside each training fold; otherwise information from the validation fold leaks in.

    Lesson: Cross-Validation & Data Leakage

  4. Question 4 of 10

    How should you cross-validate a model that forecasts next month's sales?

    1. A. Leave-one-out, so the model trains on almost all of the data
    2. B. Validate on a random 20% of months chosen from anywhere in the whole history
    3. C. Forward-chaining: train on the past, validate on the period after it
    4. D. Random k-fold with shuffling, so every month is used for training
    View answer

    ✓ C. Forward-chaining: train on the past, validate on the period after it

    Shuffling lets the model see the future. Time-ordered splits match how it will be used.

    Lesson: Cross-Validation & Data Leakage

  5. Question 5 of 10

    Only 2% of transactions are fraud. Which change needs no retraining and directly trades precision for recall?

    1. A. Moving the decision threshold
    2. B. SMOTE
    3. C. Collecting more fraud examples
    4. D. Class weights
    View answer

    ✓ A. Moving the decision threshold

    Lowering the threshold flags more cases (higher recall, lower precision) using the same model's scores.

    Lesson: Class Imbalance

  6. Question 6 of 10

    Why does random search often beat grid search for the same number of training runs?

    1. A. Grid search can't run trials in parallel
    2. B. Random search doesn't need a validation set
    3. C. It covers every combination, so it can never miss the best one on the grid
    4. D. Few hyperparameters usually matter, and it tries more values of each
    View answer

    ✓ D. Few hyperparameters usually matter, and it tries more values of each

    A 5×5 grid tries only 5 values of the important parameter; 25 random trials try 25.

    Lesson: Hyperparameter Tuning

  7. Question 7 of 10

    On a learning curve, training and validation error have converged at a high value. Will more data help?

    1. A. Yes: more data always reduces validation error in the end
    2. B. Yes, as long as you at least double the amount of training data you have
    3. C. Only if you also train for many more epochs on the new data
    4. D. Probably not: it's underfitting and needs more capacity or features
    View answer

    ✓ D. Probably not: it's underfitting and needs more capacity or features

    Converged curves at high error mean bias. More data helps when there is still a gap between the curves.

    Lesson: Learning Curves and Debugging Models

  8. Question 8 of 10

    What do SHAP values give you for one prediction?

    1. A. The model's overall accuracy on similar customers
    2. B. How much the training loss fell when each feature was first added to the model
    3. C. Each feature's contribution, summing to this prediction minus the average
    4. D. Which features the model ignored for this prediction
    View answer

    ✓ C. Each feature's contribution, summing to this prediction minus the average

    SHAP comes from Shapley values: contributions that sum exactly to prediction minus the base value.

    Lesson: Explaining Models: SHAP, Permutation Importance and PDPs

  9. Question 9 of 10

    Two features are strongly correlated. What can happen to their permutation importance?

    1. A. Both look very important, because each carries the same signal as the other
    2. B. Their importance becomes negative, because they cancel out
    3. C. Nothing; permutation importance handles correlation correctly
    4. D. Both can look unimportant, since the model leans on the other one
    View answer

    ✓ D. Both can look unimportant, since the model leans on the other one

    The model still has the information through the partner feature, so each one's importance is understated.

    Lesson: Explaining Models: SHAP, Permutation Importance and PDPs

  10. Question 10 of 10

    A logistic model outputs log-odds of 0 for a customer. What probability is that?

    1. A. 0.5
    2. B. 1
    3. C. It depends on the features
    4. D. 0
    View answer

    ✓ A. 0.5

    Probability = 1 / (1 + e⁻⁰) = 0.5. Log-odds of 0 means even odds.

    Lesson: Classical ML Practice