Do predictive analytics projects require data scientists?
Expert Mark Whitehorn explains what skills are required for predictive modeling -- and whether business users can do the work of data scientists.
Do you need data scientists on predictive analytics projects, or can business users do their own predictive modeling with current tools?
Data scientist is really just a job title. Before I answer your question, let's look at what that title implies and what skills a data scientist -- or someone doing data science work under a different title -- should have.
According to the Harvard Business Review, data scientist is "the sexiest job of the 21st century." But the term data scientist also has been described in more cynical ways on the Internet, and I would agree that defining it precisely is difficult. One of the best definitions I have yet seen is that a data scientist is "a better software engineer than any statistician and a better statistician than any software engineer."
As for skills and experience, I think coding ability and an understanding of how numbers behave are both vital, as is curiosity. Duncan Ross, director of data science for Teradata's international operations, wrote in a 2012 blog post that "insane curiosity" is the most important trait of data scientists. "In many walks of life," he continued, "evolution selects against the kind of person who decides to find out what happens 'if I push that button.' Data science selects for it."
No matter what their actual job title is, all true data scientists have started playing with some data at 8 p.m. and suddenly find it's 3 a.m. and they're still at it.
But equally important is the ability to communicate with people. If you uncover a vitally important piece of information in a set of data but are incapable of imparting it to others or convincing them of its import, it will have no impact -- and therefore, it will be as if the information were never discovered.
And that brings me to your question regarding predictive analytics projects. What you need for a successful predictive analytics project are intelligent, dedicated people who have a background in analytical techniques and can think up new, innovative approaches to problem solving.
Anyone who claims to be a data scientist should be able to demonstrate these traits, but there is no reason why they can't be found in business users. In my experience it depends far more on the people than on the job title. Of course, background and experience help, but data science is so new that many data scientists seem to be adopting the title without the requisite experience.
Learn the differences between data science and business analyst jobs
Self-service push drives new data analytics project processes
Prevent data volumes from swamping predictive analytics projects
Dig Deeper on Predictive analytics
Related Q&A from Mark Whitehorn
DBMS keys: 8 types of keys defined
Here's a guide to primary, super, foreign and candidate keys, what they're used for in relational database management systems and the differences ... Continue Reading
Key issues to consider when building a data warehouse
There are numerous issues, both technical and cultural, that organizations need to consider before building a data warehouse. Learn what they are ... Continue Reading
Six tips for improving data warehouse performance
Get six expert tips for improving data warehouse performance. Learn how database engines, SSDs and MOLAP cubes can affect your data warehouse ... Continue Reading