Have noted that the BCH signals have been a bit less beneficial recently. Lost 25% when got a BCH signal prior to crash from 325 to 250. Most recent trade (after a model update) with loss of 3.3%. Wanted to confirm the model is up to par with the recent trading data as while my gain:loss is still positive, losses are accruing a bit more rapidly than I like.
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.