2019 Innovation Name: Sydney Swans AI Audience Estimation
Awards: 10th Most Innovative Media & Marketing Company
We used a wide range of data to estimate how many tickets the Swans will sell to their home games. Using 28 years of data from Sydney Swans home games, we were able to model the impact of a number of variables, including: — Crowd Size — Round — Opponent — Score — Result — Margin — Swans Ladder Position — Opponent Ladder Position — Date — Day of Week — Time of Day — Weather.
We then used daily ticket sales from the last 3 years to understand how ticket sales at various periods before the game affected the final result. The model then uses current ticket sales and game data (ladder positions, etc), to output an estimate of ticket sales per round. An AI version of this was also created using the same data.