MKT Analytics Exam 3

The two most common techniques of cluster analysis discussed in the chapter are ________ and ________. -Schema comparisons; DAX functions -Centroid clustering; Density clustering -Distribution clustering; Connectivity clustering -K-Means clustering; hierarchical clustering

K-Means clustering; hierarchical clustering

(T/F) Market basket analysis uses purchase data to identify associations between products or combinations of products/services that frequently occur together.

TRUE

(T/F) Natural language processing (NLP) is a branch of AI used to identify patterns by reading and understanding meaning from human language.

TRUE

(T/F) Social network analysis identifies relationships, influencers, information dissemination patterns, and behaviors among connections in a network.

TRUE

Which of the following is the first step of text analytics? -Text acquisition and aggregation -Text preprocessing -Text modeling -Text exploration

Text acquisition and aggregation

____ is the process of taking the entire text data corpus and separating it into smaller, more manageable sections. -Lemmatization -Tokenization -Stemming -Corpus

Tokenization

The _____ technique counts the occurrence of words in a document while ignoring the order or the grammar of words. -Latent dirichlet allocation -N-grams -Stop words -Bag of words

Bag of words

_____ is based on the number of times a node is on the shortest path between other nodes. -Eigenvector Centrality -Degree Centrality -Betweenness Centrality -Closeness Centrality

Betweenness Centrality

The ________ structure represents groups that are larger and connected, but also have quite a few independent participants. -Support Network -Broadcast Network -Community Cluster -Brand Cluster

Community Cluster

(T/F) Instead of relying on WOM (Word-of-mouth), customers prefer online advertising directly from companies when making a purchasing decision.

FALSE

(T/F) Collaborative filtering is the use of market basket analysis techniques across stores, locations, seasons, days of the week, etc.

FALSE; Differential Market Basket Analysis Collaborative Filtering

(T/F) Cluster analysis helps marketers identify what products are being purchased together.

FALSE; Market Basket Analysis Cluster Analysis- explores data relationships, then develops smaller groups from larger populations

Which one of the following examples can aid a company to introduce new products? -Uber using social media comments about their new app to help improve the app. -Hidden Valley listening to Twitter trends to surprisingly find out that people like Sriracha and Ranch together (#sriRancha) -Amazon and Domino's using voice recognition software to take orders. -Marriott's chatbots answering questions 24/7

Hidden Valley listening to Twitter trends to surprisingly find out that people like Sriracha and Ranch together (#sriRancha)

Which of the following statements is true of the clustering process? -It enables companies to assign groups of customers to their network -It enables marketers to identify hidden structures in data -It typically assigns names and definitions to unrelated sections of data -It enables marketers to forecast revenue for next quarter

It enables marketers to identify hidden structures in data

Identify a true statement about the lift calculation in market basket analysis. -Enables us to evaluate the strength of the association -Measures the frequency of the specific association rule -A value below 1 indicates a meaningful relationship between items -Measures probability of the consequent actually occurring given that the antecedent occurs

LIFT = Enables us to evaluate the strength of the association SUPPORT = Measures the frequency of the specific association rule CONFIDENCE = Measure the probability of the consequent actually occurring given that the antecedent occurs A value ABOVE 1 indicates a meaningful relationship between items

(T/F) Agglomerative clustering is a bottom-up approach where each observation is initially considered to be a separate cluster.

TRUE

_____ denotes when network users are split into two groups with little connection between them. -Support Network -Tight Crowd -Brand Cluster -Polarized Crowd

Polarized Crowd

Which of the following is not used to measure similarity within hierarchical clustering? -Silhouette score -Jaccard's -Euclidean method -Manhattan method

Silhouette score

Which one of the following is not a type of technique used for collaborative filtering? -User to user filtering -Item to item filtering -User to item filtering

User to user filtering is NOT a technique -Item to item filtering = "Customers who liked this item also liked..." -User to item filtering = "Customers who are similar to you also liked..."

In k-means clustering, which of the following techniques can be used to identify the right number of segments? -Within cluster sum of squares (elbow chart) & Silhouette score -Euclidean distance & Manhattan distance -Within cluster sum of squares (elbow chart) & Manhattan distance -Manhattan distance & Silhouette score

Within cluster sum of squares (elbow chart) & Silhouette score