1 of 4 people found the following review helpful:
3.0 out of 5 stars An easy read on data-driven decision making, October 17, 2007

Ian Ayres book is another book extolling the virtues of data-driven decision making. In that regard it is very similar to Competing on Analytics: The New Science of Winning. The book focuses in on the power of data mining and other analytic techniques, especially when combined with random or double-blind studies and the kind of testing often called Adaptive Control (discussed, for instance, in my book Smart Enough Systems: How to Deliver Competitive Advantage by Automating Hidden Decisions. It asserts, and demonstrates with many studies and studies of studies, that this kind of data-driven decision making outperforms traditional experts essentially all the time.

While Ian is a little in love with the subject, and while he has created an unnecessary and irritating label (Super Crunchers) when he could have called these people Data Miners like everyone else, the book is well written and an easy read.

He has some fun examples - everything from the mathematical prediction of wine vintages to established stories like Harrahs and CapOne.

I liked the way in which he talks about the changing role of experts in this world. Not interpreting results but providing the subjective or face-to-face input that algorithms need to make better decisions. I think many organizations will go through a similar progression. First they might adopt a purely rules-driven or expert-centric approach. Gradually as their data, and their understanding of it, improves they might tune these rules with analytic models. Ultimately they may well find that the rules are definitively subordinate to the models with most or even all of the decision making power coming from the models. Unlike the experts in Ian's stories, one hopes the rules will not be upset by this!

One section also made a great point, highlighting in passing a potential advantage of adopting decision automation over more traditional forms of decision support. While people using decision support systems do better than people alone, they still don't do as well as the analytic model would on its own. Decision automation, with its reliance on the model, would obviate this problem.

He does not spend enough time discussing the difference between causation and correlation nor does he talk much about the constraints that can be imposed through regulation or explicit company policy. His focus is often on one-off insight that changes how organizations do something rather than on the use of this kind of decision making in high-volume, transactional systems.

Finally I agree with him that the rise of automation in decision making will force consumers to retaliate by getting access to data, and the implications of that data, to resist the ability of companies to use data to their advantage.

Overall a good book, though not perhaps as good as Competing on Analytics: The New Science of Winning. ( )

Interesting topic for all number crunchers accountants, engineers or statisticians. Brings up some new ideas on neural networks. ( )

Worthwhile reading for anyone in the data analysis, data mining, and predictive analytics fields - or who wants to understand something about those fields. Most valuable for me were the discussions on: data scraping - gathering information from online sources, the comparisons of human expertise versus simple models, and the use and uses of testing. Areas where conventional wisdom and human expertise rule the day will continue to come under attack.

It's interesting to contrast this book with "The Black Swan", by N. Taleb. In my opinion, this author (Ayers) is a "true believer" in the value of statistics, regression models, and the like. Taleb, on the other hand, rails at those who put their faith in statistical models. I think there is some middle ground, in that Taleb may agree that statistical models are useful, but users need to be wary - of unlikely events and the *impact* of those events, and knowing where the models apply and where they don't. ( )

Thoroughly enjoyed this book -- it was a quick read at just over 200 pages (before the end notes kicked in). Some basic statistical concepts are provided for the statistically challenged but that doesn't detract to any large degreee from sharing of the various Super Cruncher projects that have taken place.

Nearly overlooked in the book is the manner in which the data is obtained and the validation of the same. A regression model is only as good as the quality of the data and the manner in which the raw data is understood by the statistician. Anyone who is involved with model development will tell you that the real work is in the data prep phase. ( )

Ian Ayers is a surprisingly engaging writer, taking what many would consider a very dry topic — statistics — and turning it into a thought-provoking, but flawed, book.

From the opening pages, Ayers pits the "super crunchers" (read: people applying statistics to large data sets) against experts in an area, be it viticulture, baseball, or marketing. With barely suppressed glee he describes how number crunching out-predicts the experts time and time again. The point being that as collecting, storing and analysing large amounts of data becomes cheaper and cheaper, more and more decision-making will take the results of "super crunching" into account, with experts either having to step aside or learn some statistical chops. To back arguments for the rise of "super crunching" Ayers draws on a large number of examples from a variety of areas and even experiments with the technique himself, describing how he used it to help choose the title of his book.

Although I am more or less convinced by Ayers' arguments I found myself questioning his credibility in several places during the book. I think the main reason for this was due to the tone of the book occasionally crossing the fine line separating "enthusiastic, popular account" and "overly simplistic, gushing rave". The constant use of "super crunching" throughout the book got on my nerves after a while. It began to overemphasise the newness of what could as easily be called "statistical analysis". After a while I mentally replaced "super crunching" with the less sensational "statistical analysis" wherever I encountered it.

Conversely, Ayers constantly refers to "regression" when talking about the techniques analysts use to make predictions. At first, I thought this was a convenient short-hand for a range of techniques that he didn't want to spend time distinguishing between. It was only when neural networks are described as "a newfangled competitor to the tried-and-true regression formula" and "an important contributor to the Super Crunching revolution" that I realised that Ayers may not know as much about the nuts and bolts of computational statistics as I first thought. This impression was confirmed when Ayers later confuses "summary statistics" for "sufficient statistics" and talks tautologically of "binary bytes".

Stylistically, there is too much foreshadowing and repetition of topics throughout the book for my liking. This feels a little condescending at times, as does him directly asking the reader to stop and think about a concept or problem at various points.

Overall, I wanted to like this book more than I did. It was a light, enjoyable read and I wholeheartedly agree with Ayers' belief in the continuing importance of statistics in decision-making and his call to improve the average person's intuition of statistics. Unfortunately, I found much of "Super Crunchers" substituting enthusiasm for coherence, as well as impressions and anecdote for any kind of meaningful argument. ( )