False edge? Am i fooled by variance?

Post Reply
User avatar
jamesedwards
Posts: 2234
Joined: Wed Nov 21, 2018 6:16 pm

ShaunWhite wrote:
Sun Jun 28, 2020 5:32 am
jameegray1 wrote:
Sun Jun 28, 2020 2:14 am
Here is my latest "Think-I've-Cracked-It' automation. :roll:

500 markets in it was all roses. 1,000 markets in and it's a complete dog!
Problem is James that charts are like fractals, you don't know what zoom level you're looking at. That dip might be almost invisble after a year, and you might not know what happened before it started. How does it look if you put a trendline on that? origin zero. I'm guessing it's still +ve.
You are correct, it does. Perhaps I will try running it again once I am feeling a little richer ;)
latest v2.PNG
You do not have the required permissions to view the files attached to this post.
User avatar
jamesedwards
Posts: 2234
Joined: Wed Nov 21, 2018 6:16 pm

offlimit88 wrote:
Sun Jun 28, 2020 10:40 am

Wow that's sick, is it tennis?
No, not tennis actually. It just seemed a good example to share.
User avatar
ShaunWhite
Posts: 9731
Joined: Sat Sep 03, 2016 3:42 am

It's about understanding your edge. If you see an anomaly in the data then without a real world reason it's a prime candidate for reversion. And if you only trade +ve anomalies then you'll probably always just end up getting the worst of it.

It's like picking lottery numbers, are you the sort that chooses "6" because 6 has come out 10 times in a row, or do you choose "6" because it hasn't been out for 20 weeks straight. Personally when I see an anomaly I can't explain I oppose it rather than assuming the god of stats will keep rolling the same dice.
User avatar
Crazyskier
Posts: 1157
Joined: Sat Feb 06, 2016 6:36 pm

jameegray1 wrote:
Sun Jun 28, 2020 3:38 pm
ShaunWhite wrote:
Sun Jun 28, 2020 5:32 am
jameegray1 wrote:
Sun Jun 28, 2020 2:14 am
Here is my latest "Think-I've-Cracked-It' automation. :roll:

500 markets in it was all roses. 1,000 markets in and it's a complete dog!
Problem is James that charts are like fractals, you don't know what zoom level you're looking at. That dip might be almost invisble after a year, and you might not know what happened before it started. How does it look if you put a trendline on that? origin zero. I'm guessing it's still +ve.
You are correct, it does. Perhaps I will try running it again once I am feeling a little richer ;)

latest v2.PNG
Reversion to mean can indeed be a bitch!

I will only say that the Maria Strategy (layed horses from £1k to £100k successfully) lost many hundreds of pounds before it went on to make thousands, so patience and BIG data is key.

I spend many sleepless hours analysing each day's results, and actually think I'm on to something with the greyhounds and back odds ordering and selecting certain traps at certain courses, etc etc, but only time, and lots of it will tell. At least with dogs there are around 120 races daily to get fast input. I struggle with the horses and they don't have the bumping and barging that often sees very short-priced dogs overturned.

CS
User avatar
jamesedwards
Posts: 2234
Joined: Wed Nov 21, 2018 6:16 pm

ShaunWhite wrote:
Sun Jun 28, 2020 5:32 am

Problem is James that charts are like fractals, you don't know what zoom level you're looking at. That dip might be almost invisble after a year, and you might not know what happened before it started. How does it look if you put a trendline on that? origin zero. I'm guessing it's still +ve.
Crazyskier wrote:
Sun Jun 28, 2020 7:28 pm

Reversion to mean can indeed be a bitch!

LOL. I've set it running again on lowest possible stake. Will keep you informed ;)
User avatar
firlandsfarm
Posts: 2688
Joined: Sat May 03, 2014 8:20 am

ShaunWhite wrote:
Sun Jun 28, 2020 5:32 am
jameegray1 wrote:
Sun Jun 28, 2020 2:14 am
Here is my latest "Think-I've-Cracked-It' automation. :roll:

500 markets in it was all roses. 1,000 markets in and it's a complete dog!
Problem is James that charts are like fractals, you don't know what zoom level you're looking at. That dip might be almost invisble after a year, and you might not know what happened before it started. How does it look if you put a trendline on that? origin zero. I'm guessing it's still +ve.
As usual Shaun is on the button. :)

I do most of my betting based on graphs and statistics. The shortcoming I see in the usual backtesting graph is that it assumes you started on a particular day. What if that was a 'lucky day'? I find it more informative to plot it in reverse so instead of running a total from old to new I run it from new to old because it tells me what the value today would have been for every starting day in the past and identifies if your backtest started on a lucky day.

For example, let's assume you backed every Home team so far in the Premier league this season at Max Odds according to football-data.co.uk (with thanks to them). Your accumulated return would be …
ForwardGraph.png
… a profit so far of c.20 points (note this is an 'accidental' profit and not a recommended system!). But, +20 points only if you started on the first day of the season, what about if you started it on a different day. If you are working on a new system, you could be starting it on any day in the season so this is where I like to see what I call the 'Backward' graph where the running total is run backwards to show the total had you started on any date …
BackwardGraph.png
… Now you can clearly see that the 'system' would have been profitable whenever you started, other than a few weeks each side of the lockdown period, at around 15 points.

Obviously you would usually backtest over a longer period, this is just to show the alternative way to view the data. Hope it helps.
You do not have the required permissions to view the files attached to this post.
offlimit88
Posts: 68
Joined: Mon Feb 25, 2019 2:29 pm

Ok guys, i think we went a little bit off topic. I don t want to be right at all costs, but all these graphics you posted show a tiny edge with a lot of variability. Can anyone show me a strategy that is supposed to be 30-70 being 50-50 into a timeframe of 120 events? What are the odds of this? Just asking
User avatar
firlandsfarm
Posts: 2688
Joined: Sat May 03, 2014 8:20 am

Sorry if the input has not been very helpful offlimit88 but I'm not sure what you are asking for with "Can anyone show me a strategy that is supposed to be 30-70 being 50-50 into a timeframe of 120 events?"! :?
offlimit88
Posts: 68
Joined: Mon Feb 25, 2019 2:29 pm

firlandsfarm wrote:
Mon Jun 29, 2020 10:45 am
Sorry if the input has not been very helpful offlimit88 but I'm not sure what you are asking for with "Can anyone show me a strategy that is supposed to be 30-70 being 50-50 into a timeframe of 120 events?"! :?
If you toss a coin 120 times, what is the chance that you have 70% heads and 30% tails?
Jukebox
Posts: 1576
Joined: Thu Sep 06, 2012 8:07 pm

offlimit88 wrote:
Mon Jun 29, 2020 10:57 am

If you toss a coin 120 times, what is the chance that you have 70% heads and 30% tails?
A way to find out:
First set up a spreadsheet with the 1,329,227,995,784,915,872,903,807,060,280,344,576 different possible outcomes of 120 consecutive single coin tosses 'P' - then count up the number of of those outcomes that have exactly 84 heads 'n'. Then simply calculate n/P
User avatar
jimibt
Posts: 3641
Joined: Mon Nov 30, 2015 6:42 pm
Location: Narnia

Jukebox wrote:
Mon Jun 29, 2020 12:22 pm
offlimit88 wrote:
Mon Jun 29, 2020 10:57 am

If you toss a coin 120 times, what is the chance that you have 70% heads and 30% tails?
A way to find out:
First set up a spreadsheet with the 1,329,227,995,784,915,872,903,807,060,280,344,576 different possible outcomes of 120 consecutive single coin tosses 'P' - then count up the number of of those outcomes that have exactly 84 heads 'n'. Then simply calculate n/P
OR... you could use statistical calculations (if you don't want to wait for excel 2050) :D

https://www.universalclass.com/articles ... tcomes.htm
offlimit88
Posts: 68
Joined: Mon Feb 25, 2019 2:29 pm

Wow this is going to be interesting :D
Is there anyone smarter than me who can figure this calculation out? :D
User avatar
jimibt
Posts: 3641
Joined: Mon Nov 30, 2015 6:42 pm
Location: Narnia

offlimit88 wrote:
Mon Jun 29, 2020 2:35 pm
Wow this is going to be interesting :D
Is there anyone smarter than me who can figure this calculation out? :D
lol - if you read the article i linked, then the 2nd or 3rd worked example is almost exactly what you're after

https://www.universalclass.com/articles ... tcomes.htm
User avatar
ruthlessimon
Posts: 2094
Joined: Wed Mar 23, 2016 3:54 pm

ShaunWhite wrote:
Sun Jun 28, 2020 4:37 pm
If you see an anomaly in the data then without a real world reason it's a prime candidate for reversion.
Hence why modelled strategies are powerful. If it works long-term (good sample) & the drawdowns are manageable, the real world reasons come for free.

https://financial-hacker.com/build-bett ... d-systems/
User avatar
ShaunWhite
Posts: 9731
Joined: Sat Sep 03, 2016 3:42 am

ruthlessimon wrote:
Mon Jun 29, 2020 2:56 pm
ShaunWhite wrote:
Sun Jun 28, 2020 4:37 pm
If you see an anomaly in the data then without a real world reason it's a prime candidate for reversion.
Hence why modelled strategies are powerful. If it works long-term (good sample) & the drawdowns are manageable, the real world reasons come for free.

https://financial-hacker.com/build-bett ... d-systems/
Nice link.
Perhaps if people spent as long learning about this stuff as they do reading TiTZ, they wouldn't need to read TiTZ. It's more related to another thread but top traders don't struggle with psychology, not because they're mastered their mind but because they've mastered their craft.
Post Reply

Return to “Tennis Trading”