seen within computer vision. Its automated, frictionless and non-invasive data collection allows sportsbook operators to continue to optimise risk tolerance.
Computer vision provides a 100-fold increase in the amount of data captured compared to traditional methods, and it’s this additional information that risk managers use to improve trading performance.
For example, if you consider watching a tennis match that enters a deciding game. If we only look at past performance and scores, we will conclude that whoever was the pre-match favourite will win, right? But perhaps there is another angle to it.
In other words, computer vision can spot more latent data points that could impact the outcome of the match such as fatigue and consistency, as well as in-game patterns on key athletic movements. With this information, you may detect patterns in performance leading to new, faster and better probability estimates. Skilled bettors would maybe see this situation. If they understand it correctly the operator would potentially be exposed to more risk without that same information.
What are the challenges of translating AI's many applications to the data-rich field of sportsbook management?
P58 WIRE / PULSE / INSIGHT / REPORTS
Computer vision provides a 100-fold increase in the amount of data captured compared to traditional methods, and it’s this
additional information that risk managers use to improve trading performance.
For example, if you consider watching a tennis match that enters a deciding game. If we only look at past performance and scores, we will conclude that whoever was the pre-
match favourite will win, right? But perhaps there is another angle to it.
Te biggest challenge for operators is having access to high-quality data – that’s fundamental to any AI initiative. Without data, operators can’t feed the algorithms which ultimately means they won’t get anything meaningful out of the process. Equally important is the diversity of data. Te golden rule is typically that the amount of data required, and the timeliness (real time data makes a difference more often than not) of that data, is more than 10 times the number of parameters included in the algorithm.
In sports betting, where the models need to account for an extremely high volume of factors, acquiring enough high-quality data is exceedingly difficult. Even for operators who have a sufficient internal database, they may still lack the diversity needed to cover the entire market in the same way a global provider can. And in many cases internal information would not be enough.
According to Sportradar's data, operators rank risk management as the area of their business with the greatest potential for using AI and machine learning. Why?
Tey see it as a means of protecting their business. Te artificial intelligence available to operators allows them to process an enhanced level of betting ticket information, enabling them to examine the risk associated with a specific player account, bet or sports event, thereby limiting their financial exposure.
For example, our AI-driven automated player profiling solution analyses customer data to generate an accurate profile of a bettor’s behaviour and determine how much of a risk they are to the bookmaker.
We do not know personal data but can identify the risk a person poses to a sportsbook’s business from their betting habits. Sportradar has access to 1.5 million accounts per day, or more than 12-15 million per month. Typically,
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86
