You’re on a roll
Create a free account to save your CFA progress, track your accuracy by topic, and pick up right where you left off.
Free Questions › CFA › Quantitative Methods
Free CFA Quantitative Methods Practice Questions & Answers
1,200 exam-style Quantitative Methods questions. Pick your answer, hit Check answer, and see the worked solution — free to start, no signup.
100% free · No login to startQuestion 451
K‑means is sensitive to:
Select an option first.
Correct answer: A — Feature scaling
Explanation: Why A is right: K‑means uses distance; unscaled features distort results. Why others are wrong: B: Unsupervised → no labels. C/D: Not specific to K‑means.
Question 452
A silhouette score near –1 indicates:
Select an option first.
Correct answer: A — Points assigned to the wrong cluster
Explanation: Why A is right: Negative scores mean points are closer to other clusters than their own. Why others are wrong: B: Opposite. C/D: Not related.
Question 453
Clusters that are very far apart but internally loose may indicate:
Select an option first.
Correct answer: A — The need for more clusters
Explanation: Why A is right: Loose clusters may contain multiple subgroups → more clusters needed. Why others are wrong: B: Opposite. C/D: Not relevant.
Question 454
Structured data typically refers to:
Select an option first.
Correct answer: B — Data organized in tables with rows and columns
Explanation: Right: Structured data fits into tabular formats. Wrong: A/C/D: Usually unstructured or semi-structured.
Question 455
K-means clustering groups observations by:
Select an option first.
Correct answer: B — Minimizing distance within clusters
Explanation: K-means minimizes within-cluster distance. A/C/D: Incorrect.
Get the full CFA question bank — free
Drop your email and we'll send you fresh CFA practice questions, fully worked solutions and exam-deadline reminders. No spam — unsubscribe in one click.
Want to save your score and take a full mock exam? Create a free account →
Question 456
ARCH effects occur when:
Select an option first.
Correct answer: B — Variance depends on past squared errors
Explanation: Why right: ARCH captures volatility clustering. Why wrong: A/C/D: Not defining features.
Question 457
The complete collection of documents used for text analysis is called a:
Select an option first.
Correct answer: B — Corpus
Explanation: Why B is right: A corpus is the full set of documents used for text analytics. Why others are wrong: A = smallest text unit C = variable used in modeling D = list of unique tokens, not documents
Question 458
Lowercasing text during preprocessing is mainly done to:
Select an option first.
Correct answer: A — Reduce vocabulary size
Explanation: Why A is right: Lowercasing merges “Bank” and “bank,” reducing redundant tokens. Why others are wrong: B = not directly C = separate step D = opposite
Question 459
Removing words like “the,” “and,” and “in” is known as:
Select an option first.
Correct answer: B — Stop‑word removal
Explanation: Why B is right: Stop‑words add little meaning and are removed to reduce noise. Why others are wrong: A/C = word normalization D = splitting text
Question 460
Tokenization refers to:
Select an option first.
Correct answer: A — Splitting text into individual units
Explanation: Why A is right: Tokenization breaks text into tokens (words, subwords). Why others are wrong: B/C/D = other preprocessing steps
Question 461
Stemming is used to:
Select an option first.
Correct answer: A — Reduce word variants to a common base
Explanation: Why A is right: Stemming reduces “running,” “runs,” “ran” → “run.” Why others are wrong: B = pruning C = vectorization D = classification
Question 462
Lemmatization differs from stemming because it:
Select an option first.
Correct answer: B — Uses vocabulary and grammar rules
Explanation: Why B is right: Lemmatization uses linguistic rules to find the correct base form. Why others are wrong: A = describes stemming C = not guaranteed D = cleansing step
Question 463
A bag‑of‑words model:
Select an option first.
Correct answer: B — Ignores word order
Explanation: Why B is right: Bag‑of‑words counts tokens without order. Why others are wrong: A = false C/D = optional
Question 464
A document‑term matrix typically has:
Select an option first.
Correct answer: A — Documents as rows, tokens as columns
Explanation: Why A is right: Standard DTM structure. Why others are wrong: B = uncommon orientation C/D = incorrect
Question 465
Term frequency (TF) is:
Select an option first.
Correct answer: B — Word count divided by total tokens
Explanation: Why B is right: TF measures how often a word appears relative to total tokens. Why others are wrong: A = document frequency C = not standard TF D = vocabulary size
Question 466
Document frequency (DF) measures:
Select an option first.
Correct answer: B — How many documents contain the word
Explanation: Why B is right: DF counts how many documents contain the token at least once. Why others are wrong: A = TF in a document C = probability measure D = irrelevant
Question 467
Inverse document frequency (IDF) is used to:
Select an option first.
Correct answer: B — Reduce the weight of words appearing in many documents
Explanation: Why B is right: IDF downweights words that appear everywhere because they carry little discriminative value. Why others are wrong: A: IDF does the opposite. C/D: Not related to IDF.
Question 468
TF‑IDF is highest for words that are:
Select an option first.
Correct answer: B — Rare overall but frequent in one document
Explanation: Why B is right: TF‑IDF highlights words that are important in a specific document but uncommon across the corpus. Why others are wrong: A/D: Common words get low IDF. C: Low TF → low TF‑IDF.
Question 469
A word cloud is primarily used to:
Select an option first.
Correct answer: A — Visualize the most frequent words
Explanation: Why A is right: Word clouds visually emphasize frequent words using size or color. Why others are wrong: B/C: Not visualization tools for text frequency. D: Word clouds can show TF or TF‑IDF, not only TF‑IDF.
Question 470
Removing HTML tags is part of:
Select an option first.
Correct answer: B — Text cleansing
Explanation: Why B is right: HTML removal is a basic cleansing step. Why others are wrong: A: Engineering creates new features. C/D: Later steps.
Question 471
Replacing all numbers with a generic token like “/number/” helps:
Select an option first.
Correct answer: A — Reduce overfitting to specific numeric values
Explanation: Why A is right: It keeps numeric information without memorizing exact values. Why others are wrong: B: Not grammar‑related. C: It reduces vocabulary. D: Numbers don’t determine sentiment.
Question 472
In sentiment analysis, the most informative tokens are usually:
Select an option first.
Correct answer: B — Words strongly associated with tone
Explanation: Why B is right: Sentiment relies on emotionally charged or evaluative words. Why others are wrong: A: Stop words carry little sentiment. C/D: Not sentiment indicators.
Question 473
Mutual information measures:
Select an option first.
Correct answer: B — How informative a token is about a class
Explanation: Why B is right: MI quantifies how much a token reduces uncertainty about the class. Why others are wrong: A/C/D: Not what MI measures.
Question 474
Tokens with low chi‑square values are:
Select an option first.
Correct answer: B — Weakly associated with the class
Explanation: Why B is right: Low chi‑square means little relationship with the class. Why others are wrong: A: High chi‑square indicates strong association. C/D: Frequency alone doesn’t determine chi‑square.
Question 475
Document‑term matrices are typically:
Select an option first.
Correct answer: A — Sparse
Explanation: Why A is right: Most tokens appear in few documents, creating many zeros. Why others are wrong: B: Rarely dense. C: Rows ≠ columns. D: Normalization is optional.
Question 476
Sparse matrices occur in text data because:
Select an option first.
Correct answer: B — Most tokens appear in few documents
Explanation: Why B is right: Vocabulary is large, but each document uses only a small subset. Why others are wrong: A/D: Opposite of typical text data. C: Not related.
Question 477
Oversampling the minority class helps because it:
Select an option first.
Correct answer: A — Improves representation of minority patterns
Explanation: Why A is right: Oversampling gives the model more examples of the minority class. Why others are wrong: B: Undersampling does that. C/D: Not related.
Question 478
Hyperparameter tuning is used to:
Select an option first.
Correct answer: A — Adjust model settings for better performance
Explanation: Why A is right: Tuning optimizes model behavior. Why others are wrong: B/C/D: Preprocessing steps.
Question 479
A vocabulary is:
Select an option first.
Correct answer: A — All unique tokens in the corpus
Explanation: Why A is right: Vocabulary = unique token set. Why others are wrong: B/C/D: Not vocabulary.
Question 480
Text normalization includes:
Select an option first.
Correct answer: A — Lowercasing
Explanation: Why A is right: Lowercasing is a standard normalization step. Why others are wrong: B/C/D: Not normalization.
More free CFA topics
Economics2,066
Portfolio Management1,079
Fixed Income908
Financial Statement Analysis904
Corporate Issuers884
Portfolio Construction605
Alternative Investments540
Specialized Pathway - Private Markets500
Asset Allocation499
Derivatives498
Equity390
Performance Measurement295
Specialized Pathway - Portfolio Management253
Derivatives and Risk Management131
Ten questions in
- The ones you miss are saved as a drill you can repeat
- Your place is kept, on this device and any other
- A streak, if that is the thing that gets you back tomorrow
Every question on this page stays free and open either way.