Jun 21, 2017
We interviewed Captain Mitch Prevett on what he had to say about the first NRL DataJam.
What made you enter the Precision Sourcing’s First NRL DataJam?
Some Quantium guys joined last year and found it really fun. We really wanted to see how the First NRL DataJam works. I loved the idea of competing with other data analytics companies
How did you approach such a rich set of data, what was your strategy?
We wanted to be more insights focused and discover ground breaking findings, so our strategy was to improve on last year’s model and also leverage new models that were built for other sports like NFL. It definitely helped that most of our team members are huge fans of NRL!
What were the key insights you feel impressed and won it for you and the team?
The player selection model and the player impact (e.g. importance of hooker for Broncos)
EPA model and identifying the most effective actions to take in specific game scenarios (e.g. not a good option to run the ball on the 5th tackle, short drop out is excellent)
Highly physical games increase TV audience engagement and games with a high number of stripping penalties decrease engagement
How was it presenting and being questioned by such a knowledgeable sporting panel?
It was great to get direct feedback from those who know the game better than anyone, and could be the potential users of our insights. It gave us a much better understanding of which parts of our analysis are potentially useful in the game versus those that are less actionable
From the other presentations what stood out for you as “damn it I wish we had done that” moments?
Definitely the Facebook bot.
Any insights from the other teams you feel were particularly interesting?
The CBA presentation on the U20 player attributes that are most transferable to actual NRL which could be useful for recruiting young players
How did you celebrate the win?
By having a few celebratory drinks
For More Blogs, Click Here.
