From Business to Analytics Problems

A retail company notices declining sales but doesn't know why. Which of the following best describes the process of converting this business problem into an analytics problem?

• Hiring more sales staff to improve revenue

• Defining a measurable question such as "What factors are correlated with a decline in monthly sales over the past 12 months?"

• Redesigning the company's website without any data analysis

• Increasing the marketing budget to boost brand awareness

Which of the following is a key component when converting a business problem into an analytics problem?

• Identifying the CEO's personal preferences

• Defining the target variable or outcome that needs to be measured or predicted

• Selecting the color scheme for the final report

• Choosing the office software to be used by the team

A logistics company wants to "improve delivery efficiency." Which of the following represents the most appropriate conversion of this business problem into an analytics problem?

• "How can we hire better drivers?"

• "Can we predict which delivery routes will exceed the average delivery time of 45 minutes based on traffic, distance, and time of day?"

• "Should we buy more delivery trucks?"

• "How do we redesign our company logo?"

In the context of business-to-analytics problem conversion, what does "operationalizing a metric" mean?

• Shutting down underperforming business units

• Translating a vague business goal into a specific, measurable, and quantifiable indicator

• Hiring data scientists to manage business operations

• Writing code to automate business processes

A bank wants to "reduce loan defaults." Which of the following analytics problem statements best captures this business objective?

• "How do we increase the number of loan applications received per month?"

• "What is the probability that a loan applicant will default within 12 months, based on credit score, income, and employment history?"

• "How do we redesign the loan application form?"

• "How many employees work in the loans department?"

A healthcare provider states: "We want to improve patient outcomes." Evaluate the following analytics problem conversions and identify which one is the most strategically sound and why.

• "How many patients visited the hospital last year?" — because volume data is the most important metric

• "Which patient demographics and treatment protocols are most strongly associated with a reduction in 30-day hospital readmission rates?" — because it identifies actionable variables tied directly to the outcome

• "What is the hospital's annual revenue?" — because financial data drives all healthcare decisions

• "How satisfied are doctors with their work environment?" — because employee satisfaction determines patient outcomes

A streaming platform says: "We are losing subscribers." A data analyst must convert this into an analytics problem. Which of the following approaches demonstrates the most strategic thinking in problem formulation?

• Immediately building a machine learning model without defining the problem scope

• Identifying churn as the target variable, defining it as "cancellation within 30 days," and determining which behavioral features such as watch time, login frequency, and genre preferences predict churn

• Surveying all employees about their opinions on the platform's content

• Comparing the platform's logo design to competitors

An e-commerce company has the following business problem: "Our customers are not returning after their first purchase." A junior analyst proposes the analytics question: "How many customers made only one purchase last year?" Critically evaluate this conversion and identify the most significant limitation.

• The question is too complex and requires too much data

• The question only measures the scale of the problem but does not identify the causes or predictors needed to take corrective action

• The question is perfectly framed and requires no improvement

• The question focuses too much on future predictions rather than historical data

A manufacturing firm wants to "minimize production downtime." Two analysts propose the following analytics problems: **Analyst 1:** "How many hours of downtime occurred last quarter?" **Analyst 2:** "Which combination of machine age, maintenance frequency, and operator shift patterns is most predictive of unplanned downtime events exceeding 2 hours?" Which analyst has more effectively converted the business problem, and what principle best explains the difference?

• Analyst 1, because historical data is always more reliable than predictive models

• Analyst 2, because the question is predictive, identifies specific variables, and enables proactive decision-making aligned with the business goal of minimizing downtime

• Both analysts are equally effective because they both reference downtime

• Analyst 1, because simpler questions are always better in analytics

A marketing team presents the following business problem: "We don't know if our campaigns are working." A data analyst must design a strategic analytics problem that accounts for multiple campaign channels, customer segments, and measurable outcomes. Which of the following best represents a strategically formulated analytics problem?

• "How much money did we spend on marketing last year?"

• "Did our marketing team attend all scheduled meetings?"

• "How many social media posts did we publish last month?"