Predictive analytics for football play outcomes

30 April 2012 » Football, IBM, Writing

Inspired by the NFL playoffs in January, I wrote an invention disclosure on how to merge player statistics with current field conditions to yield a visual probability of how a play might turn out.

The end result I envisioned was that you could watch the game on television as a spectator (or in real time as a competing coach) to see what the outcome the system predicted at the start of a field goal or 3rd down pass, for example.

As a sports fan the technology adds value to what broadcasters currently provide with digital first down markers and 3D play analysis.

As a coach, you could confidently plan what your next play would be. If the likelihood of scoring a touchdown was high, you could more quickly decide whether to kick the extra point or go for a two-point conversion ahead of time.

Beyond American football, the technology could be applied to many other situations, such as ice hockey, as well as non athletic events.

  • Example Embodiment #1: Field Goal
    In the NFL, a place kicker lines up to attempt a field goal. Using statistical data about the player (his history of successful field goals from this distance in this stadium) as well as sensor or other real time data about conditions on the field, the system overlays a heat map onto the image on the television screen, showing solid orange where the kick is likely to go (and fading opacity farther away from the center based on the probability). This provides a good indication where the kick will end up, and whether it will be successful. (Figure 1)

    Figure 1: Likely outcome of field goal attempt in this context
    Example Embodiment #1: Field Goal

  • Example Embodiment #2: Pass Play
    In the NFL, a quarterback has his team lined up in a pass formation. Using statistical data about the player (his history of passes from this field position in this stadium) as well as sensor or other real time data about conditions on the field, the system overlays a heat map onto the image on the television screen, showing orange where the ball is likely to go (and fading opacity farther away from the center based on the probability) and yellow highlights the probable receiver. This provides a good indication where the pass will end up, or to which player he will pass. (Figure 2)

    Figure 2: Likely receiver of the pass and field position of the catch in this context
    Example Embodiment #2: Pass Play

  • Example Embodiment #3: Hockey shootout
    In the National Hockey League (NHL), a hockey game has goes into overtime and comes to a shootout to determine the winner. Using statistical data about the player (his history of one on one shots against this goalie in this venue) as well as sensor or other real time data about conditions on the ice, the system overlays a heat map onto the image on the television screen, showing orange where the puck is likely to go (and fading opacity farther away from the center based on the probability). This provides a good indication where the player will shoot.

IBM decided not to pursue a patent, but published the idea to protect the intellectual property. The full article is available behind a paywall at IP.com.

Would be interesting if this serves as prior art for any later invention that gets implemented.

Zend phpcloud.com at NYPHP

26 March 2012 » Cloud, New York PHP, PHP, Zend

Tomorrow night we’ll again host Edward Kietlinski at New York PHP.

He’ll talk about the latest offerings from Zend to bring your PHP applications to their developer cloud.

Soon, you’ll also be able to deploy your production-ready applications to the IBM SmartCloud.

RSVP now for Tuesday night’s meeting at IBM in midtown Manhattan.

Or, if you can’t make it in person, watch online with Cal Evans.

Migrating PHP applications to DB2

08 March 2012 » DB2, developerWorks, MySQL, PHP, Writing, Zend

IBM developerWorks has just published the final part in our series on migrating a PHP application from MySQL to DB2.

Learn why to move a PHP application to DB2, how to plan the migration, how to execute it, how to support it, and how to handle potential risks based on the experience of an IBM intranet application case study. This four-part series shares lessons from a successful MySQL-to-DB2 migration for a mission-critical PHP intranet application used by 4,000 global users within IBM to support content production for ibm.com.

In addition to sharing our own experience, the series highlights the number of resources available to you to carry out your own migration.

MongoDB and ZendCon at New York PHP

24 October 2011 » MongoDB, New York PHP, PHP, Zend

This month we have a double feature at New York PHP.

PHP on IBM System i consultant Alan Seiden will give us an update on what transpired at last week’s ZendCon.

10gen MongoDB evangelist Steve Francia will provide an overview on using PHP with MongoDB.

RSVP now for the meeting at IBM in midtown Manhattan on Tuesday October 25th or watch online starting at 6:30pm ET.

BlackBerry app for Metro-North schedules

04 May 2011 » BlackBerry, Java, Travel

Well, it took just under two years and quite a bit of marketshare loss, but I found some time to release my long promised native BlackBerry application for Metro-North commuter train schedules.

You can download NYC North Trains for free, over-the-air. I’ve tested it on OS 5 and 6 devices such as the Curve, Style, Storm 2, Bold, Tour and Torch.

Like the simple Web interface I’ve provided for nearly five years, the native app offers an interface to the MTA schedule data optimized for mobile devices.

However, it also offers some features that make the experience quite a bit more convenient for BlackBerry users.

  • Simple schedule selection using BlackBerry dropdowns and date picker
  • The ability to save your preferred origin and destination (and toggle them depending on which way you’re going)
  • Ability to email the schedule results from the device
  • Ability to save a particular departure to your calendar to block your travel time

Of course, this application comes with the standard disclaimer.

Not affiliated with the MTA or the States of New York and Connecticut. This tool uses live information directly from mta.info, so schedules are always based on the latest available information. This tool retains no copies of schedule information from the MTA.

Enjoy and let me know what other enhancements you’d like to see.

Use the IBM Cloud to build your PHP apps

14 March 2011 » Cloud, DB2, developerWorks, New York PHP, PHP, Zend

IBM developerWorks just published an article I wrote about using the Development and Test Cloud to create PHP applications.

The tutorial covers some scenarios that make the cloud compelling for PHP developers and then takes the reader through the installation of Zend Server with DB2 on the IBM Cloud.

If the content looks familiar, you may have seen an earlier version in a print copy I handed out at New York PHP (PDF) late last year.

Speaking of the cloud and NYPHP, don’t forget to join us next week to look at an alternative way to use the cloud to develop PHP applications using Amazon and RightScale.

Move from MySQL to DB2 via the Cloud

24 November 2010 » Cloud, DB2, developerWorks, Linux, PHP, Zend

IBM developerWorks has just published the first article in a series that Mark Nusekabel, Yan Li Mu and I wrote about our experience migrating a large PHP and MySQL application to DB2.

In the four part series we look at preparation, switching databases, porting code, and finally deploying the application. This first installment covers the steps to plan and resources to consult when starting a migration project.

Along with the MySQL to DB2 migration Redbook, a key technology supplementing each step in the process is the IBM Smart Business Development and Test Cloud.

If you already have access to the Development and Test pilot, the PHP developer’s guide (PDF) can give you some tips for configuring Zend Server along with DB2 using virtual machines in that cloud.

The article series and the developer’s guide may also be useful to those who have a contract for the GA version of Development and Test.

Another option to evaluate DB2 for a migration is to use the Amazon EC2 AMIs pre-configured with IBM software individually.

Or, if you’re interested in managing several instances or more complex configurations, RightScale and IBM have collaborated (PDF) to bridge the Amazon and IBM clouds.

So, if you’re considering a new relational backend for your application, the developerWorks migration series, the PHP developer’s guide for the IBM cloud, and the images within the Amazon and IBM clouds will give you a new set of tools to make evaluating the move and executing the switchover much easier.

Everything old is new again

05 August 2010 » Opinion, Thoughts, Writing

The New York Times has published two articles recently about the perception of a rise in plagiarism in the current school-age, digitally native generation:

In a highly technologized culture where information is cheap and easily copied, students can no longer be trusted or expected to make the effort to be creative, critical and original thinkers.

It’s far too easy nowadays to remix what’s already out there and in so doing, not to properly attribute a source.

Laziness and unoriginality
In the latter Times article, Sarah Wilensky – a college student herself – decries what she sees as both laziness and unoriginality in her peers. Institutions that don’t stridently enforce the rules only accelerate the disturbing trend.

“…Relaxing plagiarism standards “does not foster creativity, it fosters laziness… You’re not coming up with new ideas if you’re grabbing and mixing and matching,” said Ms. Wilensky… in a column in her student newspaper headlined “Generation Plagiarism.”

“It may be increasingly accepted, but there are still plenty of creative people — authors and artists and scholars — who are doing original work… It’s kind of an insult that that ideal is gone, and now we’re left only to make collages of the work of previous generations.”

Combining old elements
But it’s very interesting to contrast this urgent, modern lament against some thoughts from a 1965 book on advertising, “A Technique for Producing Ideas” by James Webb Young, in a chapter titled “Combining Old Elements”:

With regard to the general principles which underlie the production of ideas, it seems to me that there are two which are important.

The first of these has already been touched upon in the quotation from Pareto: namely, that an idea is nothing more or less than a new combination of old elements.

This is, perhaps, the most important fact in connection with the production of ideas…

The second important principle involved is that the capacity to bring old elements into new combinations depends largely on the ability to see relationships.

Here, I suspect, is where minds differ to the greatest degree when it comes to the production of ideas. To some minds each fact is a separate bit of knowledge. to others it is a link in a chain of knowledge. It has relationships and similarities. It is not so much a fact as it is an illustration of a general law applying to a whole series of facts…

The point is, of course, that when relationships… are seen they lead to the extraction of a general principle. This general principle, when grasped, suggests the key to a new application, a new combinations, and the result is an idea.

Consequently the habit of mind which leads to a search for relationships between facts becomes of the highest importance in the production of ideas.

Prior art is everywhere
Young argues that there’s nothing fundamentally wrong with leveraging work done by others, in fact it’s the only sensible way to make progress in a society (and run a successful ad campaign). He doesn’t ever consider attribution of these newly forged ideas in his essay.

Moving from abstract ideas to a concrete example, consider a beautiful and unique building near you. It’s largely created from well accepted architectural patterns, common construction tools, and zoning standards. You don’t see attributions on these edifices. They’re not in the blueprints or on the cranes either.

Maybe educating students and aspiring authors to properly credit their sources is the wrong approach altogether. In many ways, it’s a distraction from original thought and pure innovation.

A proposal for a read-mostly society
I believe it should no longer be the burden of the student or writer or speaker to quote his source… it should be assumed, by default, he is building on the work of others and attempting to convey a new idea built on those foundations.

Instead, it should now be up to the reader to accept that the work is derivative and take on the responsibility to vet the work.

Current plagiarism software should instead help suggest attributions… it does, in fact, rely on the same technology to check content against an existing pool of sources. With networked e-book readers and smartphones paired to efficient search algorithms, this should become ever easier.

How can you tell if a piece of work contains original research, legitimate sources or draws reasonable conclusions? Use the reader technology, find the sources and judge for yourself.

Beyond lifting the burden on authors to free them to focus on their original idea, this shift would empower readers to engage their critical thinking facilities through constant and simple source checking. This approach could also neutralize writers with an agenda who may decide to remix ideas selectively to skew a point.

In a technological society formed mostly of passive content consumers and relatively few active content producers this can only be a good thing.

Footnote
Oh, and as far as the unoriginal title to this blog post. Who should I attribute it to, Duke University or the Barenaked Ladies?

I’ll let you and Google decide.

« Previous pageNext page »