Section 004, Instructor: Larry Dignan

Lawrence Dignan

1 2 3 7

Primer on descriptive, prescriptive, predictive analytics

I found the reading this week–beyond the people analytics one–to be a bit lacking on what we’re talking about on Monday. So I aggregated some items that better define descriptive, prescriptive, and predictive.

The semi wonky textbook definition of the flavors of analytics go like this:

  • Descriptive analytics is a preliminary stage of data processing that creates a summary of historical data to yield useful information and possibly prepare the data for further analysis. … Diagnostic analytics is a deeper look at data to attempt to understand the causes of events and behaviors.
  • Prescriptive analytics is the area of business analytics (BA) dedicated to finding the best course of action for a given situation. Prescriptive analytics is related to both descriptive and predictive analytics.
  • Predictive analytics is the branch of the advanced analytics which is used to make predictions about unknown future events. Predictive analytics uses many techniques from data mining, statistics, modeling, machine learning, and artificial intelligence to analyze current data to make predictions about future.

But this post explains it a bit better.

  • Descriptive Analytics, which use data aggregation and data mining to provide insight into the past and answer: “What has happened?”
  • Predictive Analytics, which use statistical models and forecasts techniques to understand the future and answer: “What could happen?”
  • Prescriptive Analytics, which use optimization and simulation algorithms to advice on possible outcomes and answer: “What should we do?

As does Quora.

And finally, this post from my site has a handy Gartner chart that sums of the continuum. Most companies are in the descriptive and diagnostic phase of analytics and trying to get to the predictive and prescriptive part (think Watson, AI etc) where there will be some technology/model/AI that tells you what will happen and how to act.


Reading Quiz #10: Complete by Dec. 3

Some quick instructions:

  • You must complete the quiz by the start of class on Dec. 3, 2018.
  • When you click on the link, you may see a Google sign in screen. Use your AccessNet ID and password to sign in. It will then take you to the quiz.
    If it says you don’t have access, make sure you’re signed out of your regular Gmail (non-TUMail) account!
  • You can only do the quiz once. If you submit multiple times, I’ll only use the first (oldest) one.
  • This is “open book” – you can use the articles to answer the questions – but do not get help from anyone else.

Ready? Take the quiz by clicking this link.

Extra credit assignment due Dec. 3

For one point added to your final grade, here’s what I’m looking for. Read these following three Q&As and give me 100 words on one of them (your choice).

  1. Death and data science: How machine learning can improve end-of-life care
  2. A day in the data science life: Salesforce’s Dr. Shrestha Basu Mallick
  3. The data science life: Intuit’s Ashok Srivastava on AI, machine learning, and diversity of thought

The 100 words should focus on one of the following:

  • What are the challenges with this topic in regards to data science?
  • How do you foresee analytics affecting the fields that are in the interviews (end of life care, sales assistance and product development)?
  • What was your biggest takeaways from these data scientists?

This will be due on Dec. 3 to me before class via email.

1 2 3 7