Big Data

What are the three Vs of Big Data?

Volume (How much data is being generated, the scale). Variety (The types of data being generated, structured, semi-structured, and unstructured, also includes sources). Velocity (The speed at which data is being generated).

What does Big Data require to be useful?

Requires cost-effective, innovative forms of information processing to enable insight and decision making.

What is the difference between information and data?

Data is the raw numbers without any context. Information is data with context, allowing you to create predictions and assumptions based off this data. For example the number 5 is data. Once you say it is the number of red shirts, it becomes information.

What is structured data?

Data that can be arranged neatly into a spreadsheet. Eg, numbers, labels, formulae.

What is unstructured data?

Unstructured data is SMS (Text), MMS (Image), audio, video, radio waves, GPS, anything that doesn’t fit into a spreadsheet.

What are the characteristics of velocity?

Velocity relates to speed. Must be processed in real time to become useful. This means new tools and technologies. For example, data that’s constantly being streamed must be analysed in real time, such as GPS, weather forecasts, etc.

What are the four types of data analysis?

Historical: Descriptive (What happened), Diagnostic (Why it happened). Future: Predictive (Forecasts what might happen), Prescriptive (What can we do based on this forecast).

What are the characteristics of Historical data analysis?

Uses data mining and combines with other data to provide insight into the past. It summarises raw data to make it understandable by humans. It allows us to learn from past behaviours, and understand how they may affect future outcomes.

What are the characteristics of PREDICTIVE data analysis?

Uses statistical models and forecast techniques to predict the future based on probabilities. Uses systems such as ERP, CRM, HR, and POS to capture relationships between data (systems probably not necesary to remember). Predictive analytics are used to predict LIKELY OUTCOMES.

What are the characteristics of PRESCRIPTIVE data analysis?

Prescriptive analysis uses the outputs of predictive data analysis in combination with optimisation and simulation algorithms to advise on what actions to take. It is the next step in autonomous decision making, robotics, and artificial intelligence, as it allows machines to make decisions and take actions.

What are the differences between predictive and prescriptive data analysis.

Predictive analysis makes predictions on likely outcomes using statistical models and systems. Prescriptive data analysis recommends what actions to take based on the likely outcomes from predictive analysis.