CompTIA DY0-001 Dumps Questions Answers

→ Greedy algorithms make decisions based on what appears to be the best (most optimal) choice at that current moment — i.e., a locally optimal decision — without regard to whether this choice will yield the globally optimal solution.

Examples in machine learning:

Decision Tree algorithms (e.g., CART) use greedy approaches by selecting the best split at each node based on information gain or Gini index.

Why the other options are incorrect:

A: This refers to Bayesian updating, not greedy behavior.

B: That describes exhaustive search, not greediness.

C: That aligns more with probabilistic or generative models, not greedy strategies.

Official References:

CompTIA DataX (DY0-001) Official Study Guide – Section 4.2 (Model Selection Methods):“Greedy algorithms make locally optimal decisions at each step. Decision trees, for instance, use greedy splitting based on current best criteria.”

Elements of Statistical Learning, Chapter 9:“Greedy methods make stepwise decisions that maximize immediate gains — they are fast, but may miss the global optimum.”

—

→ Linear Discriminant Analysis (LDA) is a supervised classification method used to predict a categorical target (such as travel destination) based on multiple input features. It models decision boundaries between classes — which is appropriate when predicting a fixed set of destinations.

Why the other options are incorrect:

B: k-means is unsupervised and doesn't use labeled output like travel destination.

C: Latent Semantic Analysis is used for extracting relationships from textual data — not categorical prediction.

D: PCA reduces dimensionality but doesn’t classify.

Official References:

CompTIA DataX (DY0-001) Official Study Guide – Section 4.1:“Linear Discriminant Analysis is used when the response variable is categorical and the objective is classification.”

Classification Techniques Guide, Chapter 7:“LDA excels in multi-class prediction when the input data is continuous and the output is a known category.”

—

→ Multicollinearity occurs when independent variables are highly correlated with each other. This can distort coefficient estimates and reduce model interpretability. A correlation matrix is the primary tool used to detect it.

Why the other options are incorrect:

A & C: Under/oversampling relate to class imbalance, not variable correlation.

D: Overfitting is related to model complexity, not directly observable via a correlation matrix.

Official References:

CompTIA DataX (DY0-001) Study Guide – Section 3.2:“Correlation matrices are used to detect multicollinearity — high correlations among predictors that may destabilize models.”