APCompSci - Big Data - Unit 5

APCompSci - Big Data - Unit 5

Big Data

Data set that. is so large that traditional processing is inadequate to process it

Metadata

Data about other data (mean,median,mode, standard deviation, etc.)

Usability

Degree to which data can possibly or reasonably be used

Usefulness

Degree to which someone would want to use data, the data has value to some purpose.

Privacy

Protecting useful digital data from being given to or used by others

Utility

Sharing personal digital data to receive something of value in return

Confidence

Degree to which integrity of data is complete

Data Persistence

Digital information has the tendency to not be deleted because of the use of copying information

Structured Data

Data that is identifiable because it is organized in a structure, requires less storage

Unstructured Data

Data collected in "raw" form, but connections and relationships among parts of the data is harder to trace and slower to process

Data Mining

Extract information from a data set using various techniques to discover patterns of the information

Association Rule Mining

Link between one set of items and another set: instances of which the appearance of items implies that another set of items will also appear

Anomaly Detection

The identification of unusual data records that may be interesting or simply data errors and require further investigation (outlier data)

Clustering

Task of discovering groups and structures in the data that are in some way or another similar without using known structures in the data

Classification

Task of generating known structure to apply to new data

Summarization

Providing a more compact representation of a data set including visualization and report generation. Ex: Wordle,WordItOut

Regression

Attempt to find a function that models the data with the least error

ReCAPTCHA

Revision of Completely Automated Public Turing test to tell Computers and Humans apart; digital tool used to deter automated form-filling

Crowdsourcing

A sufficiently large sample size of individuals asked to estimate an unknown result, the "wisdom of the crowd" phenomenon

Screen Scraping

The conversion of data formatted for human use to a format more easily used by automated computer processes

Descriptive Analytics

Analytics that provide information about collected data via. statistics like mean, median, and mode

Predictive Analytics

Analytics that provide information about future events based on previously collected and analyzed data

Prescriptive Analytics

Analytics that provide information to maximize the chances of a future event occurring based on comparing the predictive analyses of multiple options