Skip to main content

Descriptive vs predictive data mining

Short answer

Data mining discovers interesting, previously unknown patterns from large data sets. Descriptive mining describes existing data using clustering, association and summaries, mostly unsupervised. Predictive mining builds models from training data to predict unknown values using classification, regression and forecasting, mostly supervised. The goal of descriptive is what happened; predictive is what will happen.

What is Data Mining? Differentiate between descriptive and predictive Data Mining.

Data mining is the process of discovering interesting, previously unknown and useful patterns from large data sets, using techniques of statistics, machine learning and databases.

PointDescriptive data miningPredictive data mining
GoalDescribe the general properties of existing dataPredict unknown or future values
Question"What happened? What patterns exist?""What will happen?"
ApproachPresents the data as groups, rules and summariesBuilds a model from training data and applies it to new data
LearningMostly unsupervisedMostly supervised
TechniquesClustering, association rules, summarisation, sequence discoveryClassification, regression, time-series forecasting
OutputClusters, rules, characteristicsClass label or numeric value
ExampleGroup customers by buying behaviour; find that bread and butter are bought togetherPredict whether a loan applicant will default; forecast next month's sales

✓ Answer checked by Claude Opus 5.5 (high effort)

All Data Mining chapter 1 questions →