Datamining

Data mining

Process of searching and analysing large amounts of data in order to identify patterns and extract useful information.

• Searches for relationships between facts / components / events that may not be obvious 

• May include pattern matching algorithms 

• May involve anomaly detection algorithms

• Used for business modelling 

• Used to plan for future eventualities

Who uses datamining?

• Supermarkets

• Police

• Health

• Social Media

• Financial organisations

• Many more…

Why is data mining useful / advantages

• Can identify ways to save money

• Can help focus marketing

• Can identify health trends

• Can identify groups of people likely to default on debt

Drawbacks of data mining

• Expensive – it needs large computers and skilled programmers and mathematicians

• Results can be difficult to interpret

• Can be difficult to anonymise

• Can feel creepy when marketing is targeted

• Biased data can produce biased results (e.g. sentencing or mortgage applications)

• You can get spurious (false) correlations - these will just randomly arrise with large enough data sets

Aggregated data

Process where raw data is gathered and expressed in a summary form for statistical analysis