- August 21, 2019 at 6:00 am #5306kwParticipant
Would there be a way to improve the stop loss mechanism so that the trade will actually close closer to the suggested stop loss?
For example the last BTC auto trade:
It opened with a long at $10,722.82 with a stop loss of -1.0%. The trade optimally should have closed at $10,615.59. However, the bot did not close the trade until $10194.34, which realized an actual loss of -4.93%.
So that’s a difference of nearly 4%, which could really add up over time if the bot is not able to stop out at close to what ML is suggesting. I realize there was a big red candle which I’m sure played into this.
So I’m wondering how does the bot handle stop losses? Does it place stop orders or just market sell when a certain price is hit? If it’s the latter, can it be improved by actually placing stop orders when the trade is opened?
- August 21, 2019 at 9:21 pm #5315
Hello @wahnker, you ask very sharp questions…this one has a two part answer. 🙂
This slippage can occur:
1. When you get a big red candle
2. While our systems are processing the data
The first cause is standard and will impact any trader and any system.
The second is specific to us, so let me dive into that one.
Our application pulls data and calculates against it fairly quickly, but it’s not pulling and responding every second.
The good news is we have spent the last few weeks focused exclusively on performance. The ML and calculation portion has been almost entirely refactored and we now have performance that is orders of magnitude better.
What this means is we can turn up the rate of data pulls. But we need to do this cautiously and with the right quality assurance. We will get a new roadmap update posted with this info.
This is where doing ML right gets tricky. We are running a proprietary data set. So if we change the rate, we need to wait until we have enough data in this new schema before we can begin training. This isn’t something we can do overnight. Because of this, there is a gap between changes in the foundation of data structure and when we can start making a new model generally available.
With all of that said, for the current model (considering both price and frequency slippage), the “sell” call is excepted to be within +/-0.3% of the stop loss point. So for BTC currently, the expected actual sell range is -0.7% to -1.3%.
This -4.93% definitely exceeded the expected range.
The speed of the drop was unfortunately very exceptional. Looking at the charts on Coinbase Pro, there were significant gaps on the 1 minute chart. I’d be very curious to see where -1% stops actually filled.
Finally, to answer your question–yes, you could manually enter a stop loss. It shouldn’t be required (given the expected range), but in this situation it could have helped.
- August 22, 2019 at 1:20 pm #5320kwParticipant
Thanks for the response. Keep up the good work!
- August 23, 2019 at 12:33 pm #5324martyfParticipant
Ah, so the stop loss that the bot is executing is still somewhat dynamic? I.e., the bot isn’t just getting a data feed and assessing whether the price has gone 1% lower than the long price?
It’s evaluating whether to close the trade?
in general im curious how the ML will integrate this painting of candles. It seems it was swindled by that recent move.
- August 25, 2019 at 10:21 pm #5574Marc108Participant
@justin so the bot isn’t setting a hard stop?
- August 26, 2019 at 1:53 pm #5583
Hi @martyf, yes, it is doing both. It is assessing it’s own logic for closing but also checking with the stop loss. The issue arises when price makes a large move between checks. This is rare but can, unfortunately, happen.
@Marc108, that’s right–it isn’t entering a stop order on the exchange. It’s more for its internal logic. But we do have that on the development board to review.
- August 27, 2019 at 2:59 am #5586matthew55Participant
please allow me to ask a question and understand everything properly…
Right now, the stop-loss mechanism embedded in the auto-trade feature does NOT set up any real stop-loss order on any exchange…
Instead, it’s only used internally by your algorithm in order to evaluate when is the right moment to market sell the coins…
Is it right? Or is there anything else I misunderstood/missed?
Thank you as always, Matteo
- August 27, 2019 at 6:36 pm #5588
Yes, you’re exactly right!
So it uses that percentage for its internal processing. It is not setting a stop with the exchange.
We are shooting to layer in a trailing stop too…with the goal of protecting profits even more than today. More to come there. 🙂
- You must be logged in to reply to this topic.