IPT - Ideas spawned from the data experience

Football, Soccer - whatever you call it. It is the beautiful game.
Post Reply
sionascaig
Posts: 1053
Joined: Fri Nov 20, 2015 9:38 am

jimibt wrote:
Tue Mar 16, 2021 9:39 am

In short, it's going to be quite some time until full scale AI is available, so how far can we get with data in 2021 !?!
AI tools are already available through :

https://cloud.google.com/ai-platform-un ... 1611054390

I've been messing about with it with some cricket data. Fairly straightforward tutorial... Basically get your data, specify the items you want to "learn" & the platform will select the most appropriate AI engine for your purposes..

It will run your data and give you a report on accuracy of model etc...

There is a $300 dollar credit available atm to although the processing costs seems to be relatively cheap..

It looks like you can link the engine up to live data feeds to give realtime decisions..
User avatar
jimibt
Posts: 3641
Joined: Mon Nov 30, 2015 6:42 pm
Location: Narnia

sionascaig wrote:
Tue Mar 16, 2021 10:22 am
jimibt wrote:
Tue Mar 16, 2021 9:39 am

In short, it's going to be quite some time until full scale AI is available, so how far can we get with data in 2021 !?!
AI tools are already available through :

https://cloud.google.com/ai-platform-un ... 1611054390

I've been messing about with it with some cricket data. Fairly straightforward tutorial... Basically get your data, specify the items you want to "learn" & the platform will select the most appropriate AI engine for your purposes..

It will run your data and give you a report on accuracy of model etc...

There is a $300 dollar credit available atm to although the processing costs seems to be relatively cheap..

It looks like you can link the engine up to live data feeds to give realtime decisions..
interesting - i've been using the ML.Net component in .net to do pretty much the same thing (using time based regression model). Still has a way to go as the actual sample data is of course king in all of this, so many revisions are required.

i'm still thinking about the traditional approach on this and in particular (becuase it is widely available), the IPT data and it's mix within the betfair odds etc.
sionascaig
Posts: 1053
Joined: Fri Nov 20, 2015 9:38 am

It looks ideal if you are a fairly competent trader: capture market data, capture trades, capture outcome ==> feed into model & should be able to build a baf in no time )
Archery1969
Posts: 3193
Joined: Thu Oct 24, 2019 8:25 am
Location: Newport

This i am going to like this thread allot. :)
sniffer66
Posts: 1666
Joined: Thu May 02, 2019 8:37 am

I think you know I'd be all over this Jim.

I'm using IPT PI data to drive some relatively simple strats already, alongside market data.

Does anyone know what formulas are used to derive PI1 and PI2 figures ? I know they are a mix of SOT's, pressure, corners etc over the previous x minutes
I'm currently pulling tons of API data for footy, which has quite a few more stats than those used by IPT. But the IPT stats have been tested for many years so assume they work well as is...
User avatar
ODPaul82
Posts: 683
Joined: Sun May 08, 2011 6:32 am
Location: Digswell Herts

If you hover over the information icon above each of them on the scanner it explains how they're derived
I'm pretty sure they are detailed in a video but just in case they aren't I don't want to publicly say as it's still propiretary information how they're calculated.
footysystems
Posts: 165
Joined: Thu May 09, 2013 5:57 pm

jimibt wrote:
Tue Mar 16, 2021 10:09 am
Euler wrote:
Tue Mar 16, 2021 10:08 am
A Bet Angel user has created / is creating a more complex version of this sort of thing. I'll chat to him and see if he wants to join in. It will be a publically available product.

is this Lee's InplayKing??
That's me 🤣
User avatar
jimibt
Posts: 3641
Joined: Mon Nov 30, 2015 6:42 pm
Location: Narnia

footysystems wrote:
Tue Mar 16, 2021 1:13 pm
jimibt wrote:
Tue Mar 16, 2021 10:09 am
Euler wrote:
Tue Mar 16, 2021 10:08 am
A Bet Angel user has created / is creating a more complex version of this sort of thing. I'll chat to him and see if he wants to join in. It will be a publically available product.

is this Lee's InplayKing??
That's me 🤣
well, hello -discovered IPK a while ago and it stuck in my mind... got a feeling you may well be the one to add a LOT to this thread.. looking fwd :D
footysystems
Posts: 165
Joined: Thu May 09, 2013 5:57 pm

Yes can do but it's not as easy as it looks :shock:
footysystems
Posts: 165
Joined: Thu May 09, 2013 5:57 pm

The trouble is you have to be very choosy what you play in my experience. There are far to many pitfalls just trading inplay football games. I get data on every single match each day that is played, it almost overkill.
What I found over the years is there are teams that are just that bad no matter how many DA SOT and so on they just cannot score BUT the rest of the world knows that too. It's a very fine line between profit and loss. But having said that would be great to see this thread through up some ideas on how the main man pulls it off ??
User avatar
ODPaul82
Posts: 683
Joined: Sun May 08, 2011 6:32 am
Location: Digswell Herts

If I were him then it would be watching the game alongside utilising pre-match research and in-play stats, a shot off-target in data doesn't say whether it was a close shot by the post or the player taking aim at a seagull in Row Z.

Also believing in their process & staying disciplined with proper risk management/staking.
There will be red screens that aren't shown, red screens don't sell courses.
footysystems
Posts: 165
Joined: Thu May 09, 2013 5:57 pm

Ok let's have a go 😊 pre match my ratings tell me Cremonise are well ahead of Virtus currently well ahead inplay Cremonise.

2.28 on betfair ✅
footysystems
Posts: 165
Joined: Thu May 09, 2013 5:57 pm

There is the goal price into 1.28 :D
rik
Posts: 1583
Joined: Sat Jan 25, 2014 5:16 am
Location: London

ODPaul82 wrote:
Tue Mar 16, 2021 3:24 pm
If I were him then it would be watching the game alongside utilising pre-match research and in-play stats, a shot off-target in data doesn't say whether it was a close shot by the post or the player taking aim at a seagull in Row Z.
are you sure that some close misses make a goal much more likely than a couple shots into Row Z?
The player/team suddenly lost their skill or confidence and much more likely to miss the next chance as well?
Think intent of the teams is the main factor and Psychoff was somewhat describing that as well in the intterview i saw
User avatar
ODPaul82
Posts: 683
Joined: Sun May 08, 2011 6:32 am
Location: Digswell Herts

That's my exact point, if a team is hitting & hoping then that will still just be shown as a shot in data
Data is quantifiable but doesn't contain qualative information.
Post Reply

Return to “Football trading”