OK - I know the simplest answer. Win. That all makes sense. But it feels passive to me, in the era of deep learning and advanced analytics.
A scenario:
We have two season ticket packages:
1. Super high price without purple loyalty rebate: Presumes visiting fans will go to the game, etc.
2. Same price with 50% season-end rebate: For 'Cats fans that pledge not to let the tickets go to visiting fans
Its not hard to program a model and install a few cameras to a) scan the seats. b) analyse colours (eg of what people are wearing) c) flag likely cases of visitor fan incursion
Let's say that if you want the rebate, we allow a "grace" insursion or two, just in case there's some machine error.
People who keep the pledge get 50% back at year's end, or perhaps even more if they apply it to next year's season tickets.
We have a Tech, they do tech stuff. Why not embrace data and apply it to hoops in the nerdiest, most ruthless way possible?
A scenario:
We have two season ticket packages:
1. Super high price without purple loyalty rebate: Presumes visiting fans will go to the game, etc.
2. Same price with 50% season-end rebate: For 'Cats fans that pledge not to let the tickets go to visiting fans
Its not hard to program a model and install a few cameras to a) scan the seats. b) analyse colours (eg of what people are wearing) c) flag likely cases of visitor fan incursion
Let's say that if you want the rebate, we allow a "grace" insursion or two, just in case there's some machine error.
People who keep the pledge get 50% back at year's end, or perhaps even more if they apply it to next year's season tickets.
We have a Tech, they do tech stuff. Why not embrace data and apply it to hoops in the nerdiest, most ruthless way possible?