For forecasting next year's sales and customer satisfaction, which data attribute types are typically used?

Enhance your skills with the CompTIA Data+ Certification Test. Engage with flashcards, tackle challenging multiple choice questions, complete with hints and explanations. Get yourself exam-ready now!

Multiple Choice

For forecasting next year's sales and customer satisfaction, which data attribute types are typically used?

Forecasting benefits from using data attributes that offer both precise measurements and meaningful order. Numerical attributes are quantitative and can be directly used by most forecasting models—think past sales figures, prices, or marketing spend. Ordinal attributes capture an inherent order without assuming equal spacing between levels, such as customer satisfaction ratings on a 1–5 scale or quality rankings. These two types together give models strong signals: exact quantities from numerical data and the ranked information from ordinal data, which helps predict both numeric outcomes like next year’s sales and related judgments like anticipated satisfaction. Other options don’t fit as well because a boolean is just a binary flag and an array is a data structure rather than a single attribute type. Mean and median are statistical measures, not data attribute types themselves; standard deviation and constraints describe data behavior or quality rather than the kind of attribute you’re using for forecasting.

Forecasting benefits from using data attributes that offer both precise measurements and meaningful order. Numerical attributes are quantitative and can be directly used by most forecasting models—think past sales figures, prices, or marketing spend. Ordinal attributes capture an inherent order without assuming equal spacing between levels, such as customer satisfaction ratings on a 1–5 scale or quality rankings. These two types together give models strong signals: exact quantities from numerical data and the ranked information from ordinal data, which helps predict both numeric outcomes like next year’s sales and related judgments like anticipated satisfaction.

Other options don’t fit as well because a boolean is just a binary flag and an array is a data structure rather than a single attribute type. Mean and median are statistical measures, not data attribute types themselves; standard deviation and constraints describe data behavior or quality rather than the kind of attribute you’re using for forecasting.

More practice questions