Profitable automation suddenly loss making

[jamesedwards]

everytime i raise stakes , start thinking of holidays and a 2nd income i seem to go on a long losing run.

Don't underestimate the importance of stake. Raising stakes is often the issue and I went through many automation failures before the penny dropped for me.

[gazuty]

So I've managed to pinpoint the times of day that I'm getting filled in, I'm pretty certain by someone/AI that's worked out what I'm doing and is spoofing during low liquidity periods.

Yep. Something I also discovered and learned the lesson.

I had an automation, which I ran too early. There are (at least in some markets) other automations that look for value/ anomolies etc, and that other automation just (mercilessly) milked my automation over and over and over - would have been easier to contact the counterparty and organise a direct bank transfer .

However, being milked like that gave me an idea, similar to the Fat Finger bot, but more nuanced.

[Anbell]

So I've managed to pinpoint the times of day that I'm getting filled in, I'm pretty certain by someone/AI that's worked out what I'm doing and is spoofing during low liquidity periods.

Yep. Something I also discovered and learned the lesson.

I had an automation, which I ran too early. There are (at least in some markets) other automations that look for value/ anomolies etc, and that other automation just (mercilessly) milked my automation over and over and over - would have been easier to contact the counterparty and organise a direct bank transfer .

However, being milked like that gave me an idea, similar to the Fat Finger bot, but more nuanced.

Getting your pockets emptied like that can turn into a very lucrative opportunity

[Shaung89]

Hi all

After a number of iterations, came up with a profitable set of rules for trading on all US/UK/IRE racing.

Over a period of over 2 months, only had 5 losing days (small losses at that). Overall ROI on stakes just over 3%.

Then suddenly over the last two weeks, getting filled in all over the place and had 12 losing days and 2 winning.

Initially just put it down to variance, but feels way past that now.

Anyone had something similar happen to them? I guess if someone figures out more or less what your bot is doing, then they can spoof you and take advantage of you. Is that the most likely explanation for this drastic change in performance?

Relatively new to this, so curious what people's experiences are. Is this just part of the battle, hoping folks can't spot what your automation is looking for?

Thanks

Been a week or so now, how is this going?

I also struggle with the points in your original post so im keen to understand what did/didnt work for you.
Thanks

[ShaunWhite]

I also struggle with the points in your original post

Try randomly staking at two different levels and that will give you extra info when you analyse your matched bets, along with breaking them down by price range, side, opening bet/'closing' bet performance or net final position compared to BSP etc. The bottom line PL number doesn't tell you what is working and what isn't, and it doesn't distinguish randomness from any underlying advantage you may have.

In the OPs example the strategy appears to have stalled but it's unlikely that every part of it has failed simultaneously, and as an example maybe just the shorties have stopped working and the longshots may have got better but that's being disguised by the staking. Basically dig into how that bottom line was made up of and that way you can keep tuning if the market evolves rather than just throwing it away.

[firlandsfarm]

everytime i raise stakes , start thinking of holidays and a 2nd income i seem to go on a long losing run.

There is a theory to that bigpapaperry.

Most systems show a cyclical return of an upward trending sine wave of performance i.e. a cycle consists of returning a profit but then it reverses for a while and you lose a little before returning more profit and so it does on, hopefully always building more profit than you lose in each cycle.

So you've built a profit and you say "Hey this is working well, I'll up my stakes a little" and you do so just before it enters a 'lose' part of a cycle so you are actually losing at a faster rate than you profited!

You start to lose confidence and reduce your stakes back to the original level just as the system returns to creating a profit so you don't rebuild your lost profit as fast as you lost it. And so it continues!

A system should always be profitable on level stakes. If so then you should increase your stakes at the end of a losing run and reduce your stakes at the end of a profitable run, the opposite of human nature! The problem is knowing when a run is nearing it's end.