Challenges of Artificial Intelligence to Analyze Hockey Games

Bad conclusions are worse than no conclusions, especially bad conclusions drawn from bad data. Garbage in; garbage out.

Garbage data in garbage data out. This is where teams have to get better data themselves. Use your own definition of “easy” or “hard.” Sometimes it’s not about getting people in to crunch numbers. Sometimes it’s getting people to look at film to get numbers in the first place.

Coaches and Management are investing heavily into data analytics and AI but far too often the outcomes are meaningless. Coaches end up making the wrong decisions based on worthless insights.

Understand your data source and advanced analytics for what they really are and  eradicate decision making errors from AI’s predictions.

Its important to build a knowledge foundation to ensure you are not wasting too much time on AI capabilities that are flawed.

In other words, it is the validity of the data that can never be guaranteed and in no case its complete accuracy.

Indeed, AI data analytic software face several complex challenges:

The computer artificial intelligence software is often not advanced enough to discern multiple factors during play.  Requiring human interaction and interpretation.

· the human  intermediaries can also have a low level of integration and knowledge;

· the volume of physical flows and data that requires processing to scale;

The errors and breakdowns are an operational reality and quite obvious if you are pragmatic.

With these constraints, it is therefore misleading to try to guarantee the accuracy of all the data that is collected.

In reality, once the data has been collected, it is necessary to know how to bring it to life and make it speak, whether it is true or not. The knowledge we will be able to obtain from it will depend on how we decide to look at it, and therefore on the type of information we seek. Slightly changing the angle of reading will sometimes be enough to deduce new and usable information from a data “that does not speak”.

I doubt therefore I analyse….

It is also possible to take a step aside, take a different perspective, and question what information can be extracted from the data.