AI Case Study
Stratagem achieves steady returns using deep neural networks to identify betting opportunities on sports fixtures
Stratagem is using machine learning and computer vision to determine when to place bets on sports fixtures, such as football. It also sells tips to bookmakers for odds adjustment.
Consumer Goods And Services
Entertainment And Sports
As reported in The Verge, Stratagem "uses machine learning to analyze some of its data (working out the best time to place a bet, for example), but it’s also developing AI tools that can analyze sporting events in real time, drawing out data that will help predict which team will win." According to Business Insider, Strategem's "programme can not only read different data sources but decides the correct weighting to give each source. The end goal is for the model to spot "alpha" in the market — mispriced odds where Stratagem has a better chance of winning. The programme then places bets, both before and during games... [it] is also selling tips to punters generated by its programme and marketing its services to bookmakers to help fine tune their odds."
The Verge reports that "Stratagem also notes that the opportunities identified by its AI don’t consistently line up with those spotted by humans. Right now, the computer gets it correct about 50 percent of the time. Despite this, the company say its current betting models (which it develops for soccer, but also basketball and tennis) are right more than enough times for it to make a steady return, though they won’t share precise figures."
The Verge reports that "Stratagem is using deep neural networks to achieve this task — the same technology that’s enchanted Silicon Valley’s biggest firms. It’s a good fit, since this is a tool that’s well-suited for analyzing vast pots of data... The company’s software is currently absorbing thousands of hours of sporting fixtures to teach it patterns of failure and success, and the end goal is to create an AI that can watch a range of a half-dozen different sporting events simultaneously on live TV, extracting insights as it does. Stratagem’s AI makes its calculations watching a standard, broadcast feed of the match. (Pro: it’s readily accessible. Con: it has to learn not to analyze the replays.) It tracks the ball and the players, identifying which team they’re on based on the color of their kits. The lines of the pitch are also highlighted, and all this data is transformed into a 2D map of the whole game."
In addition to the computer vision in-game monitoring, The Verge reports that Stratagem "already applies machine learning to more mundane facets of betting — like working out the best time to place a bet in any particular market. In this regard, what the company is doing is no different from many other hedge funds, which for decades have been using machine learning to come up with new ways to trade."
Business Insider reports from Stratagem's CEO: "Sports lend themselves well to this kind of predictive analytics because it’s a large number of repeated events. And it’s uncorrelated to the rest of the market. And the duration of the asset class is short — things can only diverge from fundamentals for so long because then you’re on to the next one pretty quickly".
Variety of sources including publicly available datasets, Twitter feeds, videos, purchased action data, in-house data collected by 65 football analysts globally.