Forum Replies Created
Yes, that large loss was highly unfortunate. Shortly after the trade open on Aug 2, the market crashed by greater than 29% in about 2 mins. This exceeded stop losses placed on the exchange and our system. This single event gave back much of the gains made this year in the BCH trades. The following trade was also stopped out.
In analysis, it appears the ML was attempting to grab a breakout in both cases. The recent price behaviour is being trained back in and it does not conform to prior patterns.
Both ETH and BTC models do exhibit higher statistical metrics than we are able to achieve with BCH. Fortunately, they remained out of the market ahead of the flash crash thereby better protecting balance.
Please do watch for additional updates as we share them.July 18, 2020 at 12:21 pm in reply to: 5.40 Model Release Notes: Improved Risk Management #9310
Yes. The backtesting we perform is complex and not easy to share. It involves multiple steps, including:
2. General backtesting
3. Backtesting by market condition
4. Forward testing
This link provides some insight into how this may be viewed: https://crypto-ml.com/blog/machine-learning-upgrade-to-5-0-deep-neural-networks/#Statistical_Measures
In general, any enhancement improves overall backtesting results while also better handling exceptions and edge cases.July 15, 2020 at 10:31 pm in reply to: 5.40 Model Release Notes: Improved Risk Management #9304
BCH has now also been upgraded to 5.40.
This issue is now resolved and you should see current trade history.
You are correct and this has been fixed.
Of note, there is an audit performed at the end of each month to assist in catching such items.
Hello @jghoshda, unfortunately, we do not have specific data to make this determination.
While not perfect, these links are good for reference:
The primary finding is that on Binance.us, you should trade against USD. So the most liquid pair is ETHUSD.
This is in contrast to Binance.com, where the most liquid pair is ETHUSDT.
Our data has not shown any concern in terms of slippage, but you are right, the liquidity is lower. Our team does maintain accounts at both Binance.us and Coinbase Pro but have shifted the majority of funds to Binance.us.
It would be good to hear if others have had any issues.
Hi @kw, absolutely and noted.
@Ibex, thank you for pointing out this issue. The value at the top of the Member Dashboard was incorrectly being blocked, this is now fixed. The graph below was showing properly for all members.
Please confirm you are able to see it and thank you again.
Hello @juliandwillett, yes. This is described here: https://crypto-ml.com/blog/market-orders-vs-limit-orders-for-auto-trade/
For most people, Market Order is the best option. However, neither option is perfect, each with its own pros and cons.February 21, 2020 at 8:53 am in reply to: Poll: Get your vote in. What should be our next ML feature? #7677
Hi @dannys, yes API access is coming and is in fact already in alpha testing.
This poll was specifically for the machine learning team. The API/DB team has a different plate of work.
@naturelooker, no, unfortunately, this is not yet available. However, we will be developing the “Portfolio Management” feature that will allow you to trade multiple coins at the same time. There is not a firm timeline yet, but please look for additional updates as this moves forward.
All referral codes can be found here: https://crypto-ml.com/getting-started-guide/#What_exchange_should_I_use_for_trading
Thank you for confirming. It may have been a caching issue. Glad it is proper for you now.