https://www.youtube.com/watch?v=XbDmxEOj9OY
So basically they created real Artificial intelligence that plays against itself and learn stuff from scratch. This isnt the typical game AI where everything is pre scripted. They built the AI to learn by playing and accumulating lifetimes of experience.
Thinking about it, Is it possible to create an AI that can learn from betfair and trade betfair on pre race horse racing??
If they can do it for Chess, Go, and now Dota 2, i think its possible.
Elon Musk's Open AI beat world best dota 2 players
- marksmeets302
- Posts: 527
- Joined: Thu Dec 10, 2009 4:37 pm
I've been thinking about this for some time already and am trying to learn the basic algorithms required for this challenge. A potential problem I see is that there's not enough data. With games like go and chess you can create new data by just playing a new game. With betfair, you need to wait for a new race to finish. Of course you can try the same races over and over again with different decisions but it doesn't change the environment as it does in a game where you have an opponent.
Thanks for the video!
Thanks for the video!
The logic is harder to define in a real life sport IMHO. In most of the AI applications I have seen so far, it's working to rigid boundaries that can be tested and retested. How would AI know a horse is running loose? But also that it is on a circular track leading back to the start or open countryside?
Certain parts of the market are indefinable as well. If somebody is iceberging an order into the market that's a non-repeating pattern that's hard to pick up on but you can often easily see.
I'm sure it has applications, but only given the right criteria.
Certain parts of the market are indefinable as well. If somebody is iceberging an order into the market that's a non-repeating pattern that's hard to pick up on but you can often easily see.
I'm sure it has applications, but only given the right criteria.
- ruthlessimon
- Posts: 2094
- Joined: Wed Mar 23, 2016 3:54 pm
Certainly pretty scary & people need to really think carefully about their futures. If they don't; they will get replaced by AI
- marksmeets302
- Posts: 527
- Joined: Thu Dec 10, 2009 4:37 pm
To be fair that's still better than most on a monday morning
- ruthlessimon
- Posts: 2094
- Joined: Wed Mar 23, 2016 3:54 pm
loved the first reply to that video - "looks like a real delivery worker to me"
In 1903 state of the art airplane hovered for 12 seconds and covered 120 feet. 66 years later we landed in moon. Exponential technology growth can be freakin scary. I dont see any reason why AI couldn't trade markets or "watch" soccer match and bet inplay, all the technology needed is here. Just some time and fine tuning is needed..
-
- Posts: 108
- Joined: Mon Jan 23, 2012 1:10 pm
Stratagem, the startup mentioned in a recent thread, are apparently doing precisely that;
I don't see it as much of a threat to traditional trading though as they are training it by showing it historical games - once it gets to LVGs reign at Man Utd it will probably pack up through sheer boredom.
https://www.theverge.com/2017/7/6/15923 ... -stratagemStratagem’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. From this viewpoint, the software studies matches like an armchair general: it identifies what it thinks are goal-scoring chances, or the moments where the configuration of players looks right for someone to take a shot and score.
I don't see it as much of a threat to traditional trading though as they are training it by showing it historical games - once it gets to LVGs reign at Man Utd it will probably pack up through sheer boredom.
-
- Posts: 108
- Joined: Mon Jan 23, 2012 1:10 pm
It would be very challenging because unlike games there is less consistency. If I were to attempt using the same approach I would first need the ability to capture and replay a stream so the AI can replay the same race over and over using random strategies. This, of course, would need to be done across hundreds of races and indefinitely in order to keep updated with ever changing markets.