Marketing Analytics Chapters 1 and 2

A lack of marketing analytics skills can leave a company in a situation described as “information rich but data poor.”

• True

• False

Answer explanation

If a company does not have the ability to analyze its data, it makes the company data rich but information poor because without analytics skills, the company is not able to turn the data into information that would then lead to action.

In the context of data measurement types, ratios have no true zero point.

• True

• False

Answer explanation

The statement is false because ratios are a type of measurement that do have a true zero point, indicating the absence of the quantity being measured. This distinguishes them from interval measurements, which do not have a true zero.

Variables are characteristics or features that pertain to a person, place, or object.

• True

• False

Answer explanation

Variables represent characteristics or features related to a person, place, or object, making them essential in data analysis and research.

The goal of unsupervised learning is to model the underlying structure and distribution in the data to discover and confirm patterns in the data.

• True

• False

Answer explanation

Unsupervised learning identifies patterns and structures in data without labeled outcomes, allowing for the discovery of relationships and distributions.

Ex: Amazon determines how likely customers who purchase one product are to purchase another then creates recommendations based on that information.

Identify a valid difference between descriptive analytics and predictive analytics.

• Descriptive analytics can identify patterns in data, whereas predictive analytics can recognize objects from an image.

• Descriptive analytics mimics human-like intelligence, whereas predictive analytics identifies the best optimal decision.

• Descriptive analytics predicts new needs and opportunities, whereas predictive analysis reinforces existing beneficial practices.

• Descriptive analytics uses data to explain the past, whereas predictive analytics uses data to explain the future.

Answer explanation

Descriptive analytics focuses on analyzing past data to understand what happened, while predictive analytics uses historical data to forecast future outcomes.

In the context of questions that help identify a business problem, asking “What factors continue to drive this problem?” will help determine the outcome of the ________.

• root-cause analysis

• market research

• financial audit

• customer feedback

Answer explanation

Asking about the factors driving a problem is essential for root-cause analysis, as it helps identify underlying issues that need to be addressed to resolve the problem effectively.

Which of the following is true about the fifth principle in the SMART analytics principles?

• The project’s goals should be specific and clearly defined.

• The project should be trackable and the outcomes measurable.

• The project should solve the analytics problem and align with the business objectives.

• The project should be completed in a timely manner.

Answer explanation

The fifth principle of SMART analytics emphasizes timeliness, ensuring that projects are completed within a set timeframe. This is crucial for maintaining relevance and achieving business objectives effectively.

A marketing analyst at a gaming company is studying the effect of school holidays on sales of video games. In this study, what type of variable is school holidays?

• an outcome variable

• a dependent variable

• a target variable

• an independent variable

Answer explanation

An independent variable is the one you are actively changing or manipulating in an experiment, while the dependent variable is the one that "depends" on the changes made to the independent variable.

In supervised learning, the training dataset is used to

• assess how well the algorithm developed using the validation dataset estimates the target variable.

• build the algorithm and “learn” the relationship between the predictors and the target variable.

• select the model that most accurately predicts the target value of interest.

• evaluate the final selected algorithm and see how well it performs.

Answer explanation

In supervised learning, the training dataset is used to build the algorithm and learn the relationship between predictors and the target variable, making this the correct choice.

In supervised learning, the testing dataset is used to

• “learn” the relationship between the predictors and the target variable.

• select the model that most accurately predicts the target value of interest.

• assess how well the algorithm developed using the training dataset estimates the target variable.

• evaluate the final selected algorithm and see how well it performs on a third dataset.

Answer explanation

In supervised learning, the testing dataset is used to assess how well the algorithm developed using the training dataset estimates the target variable, not to learn relationships. Thus, the correct choice is to assess the algorithm's performance.