Data science and predictive analytics are top of mind – but how do you get started? I had the chance to interview Eric Siegel, founder of Predictive Analytics World, the leading conference series, and author of the popular, award-winning Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, which earlier this year released its Revised and Updated edition.
There’s always a balance between learn-by-doing and more formal educational resources, and it varies by individual. I will say this, though: Even the deepest, most senior, talented expert can at times benefit by learning from others. My favorite example is uplift modeling (aka persuasion modeling – covered by the final chapter of my book, “Predictive Analytics,” or search my name and “uplift modeling white paper” for shorter but similar coverage) – even the brightest, most experienced minds I know often need a non-technical, accessible introduction to what uplift modeling really is before it fully sinks in and they go, “Bingo!”
As a grad student through the 90s I loved the abstract idea of machine learning and so I dug in deep in certain areas. As a newbee without much breadth, I reinvented a lot that I later found was standard, which is actually an effective way to learn when you are young and have time. Later as a professor, I taught the machine learning graduate level course (at Columbia), and found how much teaching helps one learn. Finally, in the last thirteen years as an independent consultant, especially chairing the Predictive Analytics World conference series, I gained immensely by hearing from experienced industry practitioners (as well as by doing – does that go without saying?).
For the best I can do to address that question, here’s a blurb from the new preface to the recently Revised & Updated edition of my book, “Predictive Analytics”:
Uh, well practitioners do create great content in this industry (both written and presentations). I would say the most misleading thing in predictive analytics to a newcomer is how many of the pertinent software solution vendors pitch either explicitly or implicitly that a solution can be plug-and-play. What is misleading there is that there is simply no way to get around the heavy data preparation task required before employing any predictive modeling software tool.
Yes, definitely – but it isn’t a how-to. You need to continue the learning process after my book. As a conceptually complete, substantive introduction and industry overview, practitioners definitely benefit from the book, in addition to newcomers. Allow me another excerpt from its preface:
Although this mathless introduction is understandable by any reader—including those with no technical background—here’s why it also affords value for would-be and established hands-on practitioners:
That said, burgeoning practitioners who wish to jump directly to a more traditional, technically in-depth or hands-on treatment of this topic should consider themselves warned: This is not the book you are seeking (but it makes a good gift; any of your relatives would be able to understand it and learn about your field of interest).
As with introductions to other fields of science and engineering, if you are pursuing a career in the field, this book will set the foundation, yet only whet your appetite for more. At the end of this book, you are guided by the Hands-On Guide on where to go next for the technical how-to and advanced underlying theory and math.