datamining

Extracting hidden patterns

Datamining (also data mining) is the process of analyzing large datasets to discover patterns, correlations, or useful information.

In computing and business, it's a legitimate analytical technique: The company used datamining to identify customer trends.

The term often carries negative connotations when it describes extracting personal information from users without their full awareness: Social media platforms have been accused of datamining their users.

techniques

clustering

Forming concentrated groups

neural networks · pattern recognition · preprocessing · extraction · sampling · algorithms · machine learning · scraping · ETL

discovery

patterns

Recurring arrangements or designs

  • insightsPenetrating understandings gained
  • correlationsStatistical relationships between variables
  • trendsPrevailing directions of change

anomalies · relationships · predictions · associations · outliers · segmentation · profiling · inference · signals

infrastructure

databases

Organized electronic information collections

  • datasetsOrganized digital records
  • SQLDatabase manipulation language
  • HadoopOpen-source cluster framework

cloud computing · storage · servers · processing · queries

ethics

privacy

Freedom from observation

anonymization · tracking · profiling · cookies · targeted advertising · Cambridge Analytica · opt-out · exploitation · transparency · regulation

Opposites
method of information discovery

dataminingintuition

Instinctive immediate understanding

guesswork · casual observation · anecdotal evidence · gut instinct · chance encounter

approach to data

dataminingdata collection

Systematic accumulation of facts

data entry · primary research · field work · content creation · field research

scale and systematicity

datamininganecdote

Brief account of incident

cherry-picking · glancing · skimming · spot-checking

Family

mine, data, mining, miner, mines, mined, miners, database, datum

Familiarity
Top 500,000
Profile
Used worldwide · Timeless · Abstract · Rated G