Maximum Entropy Data Analysis of UK National Lottery using Commodity Supercomputers
Using the Maximum Entropy Method, we have estimated the popularity of each of the 14 million tickets in the UK National Lottery
From this we can deduce the popularity of individual numbers
The results were derived using a commodity supercomputer designed and built in our research group
Players prefer to pick numbers lower numbers and those towards the centre of the ticket
The entry price of supercomputing has traditionally been very high. As processing elements, operating systems, and switch technology become cheap commodity parts, building a powerful supercomputer at a fraction of the price of a proprietary system becomes realistic.
We have recently purchased a dedicated computational cluster of eight DEC Alpha workstations. Our judgement is that they are fully competitive node for node with systems from major vendors such as IBM or SG/Cray for a wide range of applications, and at a cost lower by about a factor of three. We are researching the long term goal of delivering an effective remote and local parallel computing service directly under Windows NT, with all the commensurate benefits of commercially supported software and integration into a mainstream commercial IT environment.
Commodity Supercomputing Research sponsored by and in conjunction with