Supervised Learning Models Flashcards
7 cards from real Data Science practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Supervised Learning Models flashcards as text
What does a ROC curve plot?
Answer: True positive rate vs false positive rate
The ROC curve shows the tradeoff between true positive rate and false positive rate across thresholds.
An AUC of 0.5 indicates what about a classifier?
Answer: Performance no better than random guessing
An AUC of 0.5 means the model cannot distinguish classes better than chance.
What is cross-validation primarily used for?
Answer: Estimating model performance on unseen data
Cross-validation partitions data into folds to get a more reliable generalization estimate.
Which technique handles categorical features for a linear model?
Answer: One-hot encoding
One-hot encoding converts categories into binary indicator columns usable by linear models.
What does early stopping prevent during training?
Answer: Overfitting by halting when validation loss stops improving
Early stopping ends training once validation performance degrades, avoiding overfitting.
In random forests, how is diversity among trees achieved?
Answer: Bootstrap sampling and random feature subsets
Each tree trains on a bootstrap sample with a random subset of features, decorrelating them.
What is data leakage in supervised learning?
Answer: Information from outside the training set influencing the model
Leakage occurs when test or future information improperly enters training, inflating performance.