Big Data – Blog by YY
Types of analytics
“Machine Learning,“ hot field that bursted into our attention after AlphaGo defeated professional Go players.
However, beyond confidential algorithms being used in AlphaGo, fundamental concepts for us to grab the fields are necessary.
In the weekly blog, commonly used analytics types will be introduced in the next section.
Three types of analytics have been applied since the past,
a.) Descriptive analytics
b.) Predictive analytics
c.) Prescriptive analytics
Descriptive analytics –
As its verb form, “DESCRIBE“ descriptive analytics summarize raw data and make it interpretable by human. Descriptive analytics describe the past (secs/mins/hours/years ago) where the past meaning any point of time that an event happened.
Examples of descriptive analytics are reports that provide historical insights on sales, financials, customers,
retailing, and so on.
Predictive analytics –
Predictive analytics are about understanding the future or to “Predict” what might happen.
Predictive analytics provides actionable insights against source data for companies, and likelihood of future outcomes.
One application is the use of predictive analytics to produce recommendation scores to users.
Prescriptive analytics –
New field of prescriptive analytics allows users to “PRESCRIBE” a number of possible actions and guide them towards a solution. In short, prescriptive analytics are about providing advice.
Prescriptive analytics go beyond what being mentioned above by recommending possible courses of action.
Prescriptive analytics are relatively complex to administer, and most companies are not yet using them in their business.
Examples of prescriptive analytics are to optimize production, scheduling and inventory in supply chain to make sure that are delivering the right products at the right time and optimizing customer experiences.
In a nut-shell, the summary of the weekly blog is the following,
Descriptive analytics – a kind of analytics that providing insight into the past.
Predictive analytics – as the meaning of its verb tense “PREDICT“ can be treated as a route to understand the future.
Prescriptive analytics – to go beyond the results from Descriptive and Predictive analytics and provide users with advise on what actions should take based on outcomes.