MKT 4393 – Marketing Analytics Final Exam Study Guide Spring 2025

This set of flashcards provides key terms and definitions from the Marketing Analytics final exam study guide.

SMART analytics principle

A goal-setting technique that stands for specific, measurable, attainable, relevant, and timely.

Primary data

Data collected for a specific purpose.

Secondary data

Data that relies on existing data collected for another purpose.

Structured data

Data organized in rows and columns, easily searchable and analyzable.

Unstructured data

Data without a predefined structure that does not fit well into a table format.

Discrete data

Data measured in whole numbers.

Continuous data

Data that includes values with decimals.

Categorical data

Data that represents a group of categories.

Binary categorical data

Categorical data having only two values, like yes or no.

Nominal categorical data

Data with characteristics that have no meaningful order.

Ordinal categorical data

Data with characteristics that hold a meaningful order, but uneven intervals between values.

Independent variable

The predictor or feature variable in an analysis.

Dependent variable

The variable being predicted in an analysis.

Predictive analytics

Analytics used to build models based on past data to explain future outcomes.

Prescriptive analytics

Analytics that identifies the best optimal course of action based on data.

Cognitive analytics

Advanced analytics capabilities that draw conclusions from data without being explicitly programmed.

Characteristics of Big Data

Volume, variety, veracity, velocity, and value.

Foreign key

A column or set of columns in a table that refers to the primary key in another table.

Relational data access

Accessed using structured querying language (SQL).

Aggregation (data transformation)

The process of summing data according to the unit of analysis desired.

Normalization (data transformation)

Scaling a variable by subtracting it from the mean and dividing by the standard deviation.

Dummy coding

Creating a dichotomous value from a categorical value.

Machine learning

The development of algorithms that allow computers to learn from experience.

Deep learning

Using algorithms to build neural networks for classification or prediction.

Natural language processing (NLP)

AI branch to identify patterns from human language.

Computer vision

A machine’s ability to extract meaning from images.

Exploratory data analysis

Summarizing main characteristics within data to explore trends.

Descriptive data analysis

Summarizing and interpreting historical data.

Data visualization software

Tools like Tableau, Google Data Studio, Qlik, and Microsoft Power BI.

Design principles in visualization

Balance, emphasis, proportion, rhythm, variety, and unity.

Cluster analysis

An analytical method of segmenting markets based on shared characteristics.

K-means clustering

A technique using mean values to minimize distance to observations.

Association rule

Defines relationships in datasets using if-then statements.

Support (association metrics)

Measures the frequency of a specific association rule occurring.

Confidence (association metrics)

Measures the conditional probability of a consequent given the antecedent.

Lift

Evaluates the strength of an association between items.

Text analysis steps

Text acquisition, preprocessing, exploration, and modeling.

Node (social networks)

An entity like a person or product in a network.

Edge (social networks)

Links and relationships between nodes.

Degree centrality

Centrality measured by the number of edges connected to a node.

Betweenness centrality

Measures how often a node is on the shortest path between nodes.

Closeness centrality

Measures the proximity of a node to all others in the network.

Eigenvector centrality

Measures the linkage of a node to other well-connected nodes.

Sessions (web analytics)

Total visits to a website.

Conversion rate

Percentage of sessions resulting in goal completion.

Bounce rate

Percentage of users who leave after viewing only one page.

A/B testing

Method to test the effectiveness of various versions of web ads.