MC Outlying observations which represent erroneous data are treated using... missing value procedures. correct truncation or capping. incorrect MC What statement about the adjacency matrix representing a social network is not true? It has the same number of rows and columns. incorrect It can include weights. incorrect It is sparse since it contains a lot of non-zero elements. correct It is a symmetric matrix. incorrect MC Consider a data set with a multiclass target variable as follows: 25% bad payers, 25% poor payers, 25% medium payers and 25% good payers. In this case, the entropy will be: Minimal incorrect Maximal correct MC Given the following five transactions:

T1 {K, A, D, B}
T2 {D, A, C, E, B}
T3 {C, A, B, D}
T4 {B, A, E}
T5 {B, E, D}

Consider the association rule R: A -> BD.

Which statement is correct? The support of R is 60% and the confidence is 75%. correct The support of R is 75% and the confidence is 60%. incorrect The support of R is 60% and the confidence is 100%. incorrect The support of R is 100% and the confidence is 75%. incorrect MC Clustering, association rules and sequence rules are examples of: Predictive analytics incorrect Descriptive analytics correct MC Clustering, association rules and sequence rules are examples of: Descriptive analytics correct Predictive analytics incorrect MC Clustering, association rules and sequence rules are examples of: Predictive analytics incorrect Descriptive analytics correct MC Featurization in the context of neural networks refers to... adding more nodes to the network. incorrect adding more local features to the data set. incorrect making features (=inputs) out of the network characteristics. correct selecting the most predictive features. incorrect MC Which statement is CORRECT? Decision trees essentially model a linear decision boundary. incorrect When building decision trees, overfitting occurs when the error on the training set keep on increasing. incorrect When building decision trees, the impurity can be measured with entropy, gini, MSE or ANOVA with the F-test. correct When building decision trees, we should chose the split with the lowest gain. incorrect MC Outlying observations which represent erroneous data are treated using... missing value procedures. correct truncation or capping. incorrect