Thursday, August 3, 2017

Stratagem design Machines that Gamble Like No Human can!

Listening to Andreas Koukorinis, founder of UK sports betting company Stratagem, and you’d be forgiven for thinking that soccer games are some of the most predictable events on Earth. “They’re short duration, repeatable, with fixed rules,” Koukorinis tells The Verge. “So if you observe 100,000 games, there are patterns there you can take out.”

Stratagem is a British company that takes bets on soccer games. Currently, it employs some 65 human experts who study matches across the globe and uses machine learning to automate parts of the process of betting, like figuring out when people like to gamble the most.
The mission of Koukorinis’ company is simple: find these patterns and make money off them. Stratagem does this either by selling the data it collects to professional gamblers and bookmakers, or by keeping it and making its own wagers. To fund these wagers, the firm is raising money for a £25 million ($32 million) sports betting fund that it’s positioning as an investment alternative to traditional hedge funds. In other words, Stratagem hopes rich people will give Stratagem their money. The company will gamble with it using its proprietary data, and, if all goes to plan, everyone ends up just that little bit richer.

But what's down the pike, founder Andreas Koukorinis tells potential investors and The Verge, is an AI that can watch a game in real time, and, with thousands upon thousands of data points, predict who can win. "They're short duration, repeatable, with fixed rules," Koukorinis tells The Verge. "So if you observe 100,000 games, there are patterns there you can take out." The company is raising money for a £25 million ($32 million) fund to test those patterns out.

The number of possible bets on soccer or any other sport are limited only by the imagination of the bookies, ranging from coin flips to red flags to what color shoes Beyonce will wear at halftime. So Strategem is starting with the basics, trying to get its AI to understand goal chances. Koukorinis has his AI hooked up to regular broadcasts, which can get tricky with instant replay. But the AI marks up the screen with various boxes as players slash through the midfield and make an attempt on a goalie. It's similar to what a self-driving car AI sees.

Currently, Kokorinis tells The Verge that the AI is doing 50-50 so far, which might not seem so impressive. But it took a while for SABR to catch on as well, when baseball scouts were convinced that athletic potential could only be assessed through the naked eye. Stratagem is taking a bet on betting and assuming a similar revolution is coming.

No comments:

"HarmonyOS vs. Android: Will Huawei’s Switch Hit the Right Note in Nigeria?"

  By Ejiofor Agada When Huawei officially broke free from the Android ecosystem to fully embrace its proprietary HarmonyOS, it didn’t merely...