MC Given the following statements:

i. When using featurization, the network is summarized in a set of features, such as betweenness and closeness.
ii. The betweenness of a node is its average distance to all other nodes in the network.

Which of these statements are correct? Statement i is correct, but statement ii is not correct. correct Both statements are correct. incorrect Statement ii is correct, but statement i is not correct. incorrect Both statements are not correct. incorrect MC Which statement is CORRECT? A key advantage of k-means clustering is that the number of clusters need not be specified prior to the analysis. incorrect Divisive hierarchical clustering starts from all observations in individual clusters and merges the ones that are most similar until all observations make up a single cluster. incorrect The single linkage method in hierarchical clustering defines the distance between two clusters as the biggest distance, or the distance between the two most dissimilar objects. incorrect A dendrogram can be used to decide upon the optimal number of clusters. It is a tree-like diagram that records the sequences or merges. correct MC Which statement is NOT CORRECT? An important advantage of cloud based solutions concerns the scalability and economies of scale offered. More capacity (e.g. servers) can be added on the fly whenever needed. incorrect Classification measures like accuracy, specificity, sensitivity, recall and precision are dependent on the cutoff value. incorrect The aim of clustering is to come up with clusters such that the homogeneity within a cluster is maximized and the heterogeneity between clusters is minimized. incorrect A key advantage of k-means clustering is that the number of clusters need not be specified prior to the analysis. correct MC Which of the following is not a risk when outsourcing analytics? Dilution of competitive advantage due to e.g. mergers and acquisitions. incorrect Continuity of the partnership incorrect The fact that all analytical activities need to be outsourced correct The exchange of confidential information incorrect MC Decision trees can be used in the following applications: Credit risk scoring, churn prediction and customer profile segmentation incorrect Credit risk scoring, churn prediction, customer profile segmentation and market basket analysis. incorrect Credit risk scoring incorrect Credit risk scoring and churn prediction 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 100% and the confidence is 75%. incorrect The support of R is 60% and the confidence is 75%. correct The support of R is 60% and the confidence is 100%. incorrect The support of R is 75% and the confidence is 60%. incorrect MC Which of the following is not an advantage of open source software for analytics? It has been thoroughly engineered and extensively tested, validated and completely documented. correct It is available for free. incorrect It can be used in combination with commercial software. incorrect A world-wide network of developers can work on it. incorrect MC Which of the following is not an advantage of open source software for analytics? It has been thoroughly engineered and extensively tested, validated and completely documented. correct It can be used in combination with commercial software. incorrect A world-wide network of developers can work on it. incorrect It is available for free. incorrect MC Which of the following strategies can be used to deal with missing values? Keep incorrect Delete incorrect Replace/impute incorrect All of these strategies can be applied correct MC Which statement is NOT CORRECT? The main advantage of performance measures such as ROC and AUC is their independence of the cutoff value. incorrect The diagonal of a ROC curve represents a random scorecard, whereby sensitivity equals 1-specificity for all cutoff points. incorrect The lower the area under the ROC curve (AUC), the better the model performs. correct Classification measures like accuracy, specificity, sensitivity, recall and precision are dependent on the cutoff value. incorrect