Analytics

The science of data mining, random testing, and statistical analyses to select the best alternative among a set of options.

Travel intelligence

TravelFor years, airlines have priced individual seats on different days at different levels. This can drive you nuts, if you're trying to get a good deal. It can lead to situations in which you turn to the guy on your right, and ask him what he paid, and find out he paid half what you did - even though you bought your ticket earlier than he did. It's time to fight back!

Farecast is an airline fare site mentioned in Super Crunchers. It's the best travel site for finding fares I've seen. Amazingly, once you've searched for your travel dates, it offers it's own solution and then also offers direct links to nearly all it's competition (Expedia, etc). But at least in my testing, it always beats that competition in price. But that's not the real reason to use it.  read more »

A case study of implementing systematic improvements

Person aiming arrow at targetThe term health care reform has diverse meanings for the many stakeholders involved in the US health care system. The underlying issues associated with implementing such reforms are quite complex, but pressures for reform are high. In 2005 alone, the United States spent more than two trillion dollars on health care, or over $7,100 per person, and are growing at over twice the rate of growth of our overall economy. Government and private insurance fund about 80 percent of those costs, and the rest largely comes directly (rather than indirectly) out of our pockets. About a third of these expenditures occur within hospitals; clinicians get another third, and the rest is spread across nursing homes, prescription drugs, and the costs of administering our insurance system.  read more »


Spinning the numbers

Spinning a topSpin is the process of selectively interpretting a situation in a biased way, in order to drive a particular agenda. When a particular data measurement value or trend is not well defined, in business or government, this can be particularly dangerous. This is because such spin drives decisions based upon one perception of the world, when in fact another reality may be actually occurring. For a particularly troubling example, consider this alternative view of the current economic situation. For another, consider the many financial institutions that maintained excellent credit ratings, despite large portfolios of Subprime lending.

The underlying elements which enable such spin are:  read more »


Confronting variation

Physical representation of 2003 violent crimes in LondonWe often wish, after going to the trouble of standardizing our work, and training our people, that we will see consistent outcomes as the fruit of our labors. In practice, variation prevails until we can eliminate its causes. Consider the picture on the right, which is an artist's depiction of the frequency and position of urban crimes in South London, Manchester, East London, and Eindhoven. Each individual incident of violent crimes in each area adds to the height of the model at that location. The result forms a mountainous terrain of the variation of these crime incidents by location. Such variation is the nature of populations, and a challenge to solution designers who must deal with those populations.

For an example drawn from our health care domain, consider this situation, from Health Dialog:  read more »


Show me the numbers!

Why would a casino try and stop you from losing? How can a mathematical formula find your future spouse? Would you know if a statistical analysis blackballed you from a job you wanted?

 read more »
cover of Show me the numbers!Super Crunchers: Why Thinking-by-Numbers Is the New Way to Be Smart

author: Ian Ayres
rating:
asin: 0553805401
binding: Hardcover
list price: $25.00 USD
amazon price: $16.50 USD


Passion and new knowledge beats old knowledge

Movie ratings generated by CinematchNetflix has been running their own X-prize ('Netflix prize'), a crowdsourcing competition for a million dollars to come up with a better algorithm for predicting movie preferences than the algorithm Netflix is currently using. That approach, Cinematch, currently captures 2 million new ratings (between 1 and 5 stars) per day, and is used to predict preferences ('if you liked Braveheart, you will also like...') for the 65,000 movies they rent, about 1 billion times per day. They are looking for a 10% improvement in accuracy, which doesn't sound like much, but would mean 10M of ther customers would get better matches each day - which is quite a lot, if you're trying to differentiate yourself to apture the off-line (and soon, online) rental market!.  read more »


Add to calendar