- This topic has 11 replies, 5 voices, and was last updated 1 year, 1 month ago by
.
- Posts
[quote quote=7834]We’ve been receiving 4-5 sequential signals at a very fast pace, but almost all of them have resulted in a loss…
Is there anything you can do or it’s just an “uncommon” situation?
Thank you[/quote]
I have the impression that the AI for ETH is in “ranging” mode. Visually, i imagine a flat-lining oscillator getting whipsawed into crossing above and below the zero line numerous time each time the price rises or falls. I would like to clarify with the team if this is what’s actually happening and if this is just part and parcel of trading with AI involved.
Hey everyone, @matthew55–thanks for starting this thread. We’ll need to get an official communication out.
We’ve finished reviewing the trades, updated the trade history table, and are currently performing a root cause analysis on the behavior this weekend.
As it currently stands, all systems are performing as expected. But it appears the inputs (market data points) are exceptional and highly unusual. This is, unfortunately, creating a lot of false flag trades and burning trade fees and causing unnecessary losses.
In the bigger picture context, we’re seeing crazy movement across all financial sectors.
For reference, here’s what’s going on in the Dow Jones right now:
That’s the biggest weekly decline since the 2008 crisis. This and the big other markets are likely causing different market participant behavior in the crypto markets as well.
The BCH and LTC models seem to be handling this market more effectively, so we’re looking at the deltas.
We’re targeting to have an update (if required) rolled out within the next 24 hours to minimize these false flags.
@matthew55 and everyone, here is the update on this:
Backgound and Root Cause
The 4.x Ethereum model does prefer to issue a relatively higher volume of trades, in about the 4-5 trades/month range. By artificially lowering that, we see drastic and unacceptable reductions in results.Despite expecting higher volume, the ultra-fast trading seen over the last week or so was unusual. The data coming in put us in “edge case” scenario, so we saw unusual trading behavior. In general, most financial markets have been in a highly-unusual state.
The rapid trading has slowed down without us changing anything.
Action Items
We will soon post information on each model’s expected trade frequency as well as some technical/statistical data on technology used for prediction.We will upgrade ETH to the 5.x model series within a week.
I’ve alluded to 5.x briefly before. It’s a natural progression from 4.x and are in fact very related. But they require a complete overhaul to our infrastructure. The 5.x machine learning models are massively more complex and can chug many more inputs. This takes a lot of compute power. The result is another large leap forward in prediction precision.
Once this upgrade to 5.x is complete, we will have moved to the top of the ML stack. I would just expect refinements from that point forward, but you never know–this is an evolving game.
I will note that the 5.x ETH also issues a larger quantity of trades.
Excellent! Me too. Yeah, it is really the vision of where we’ve wanted to get this platform. It’s the last major leap I see us taking for a while. To do it properly requires the right amount of expertise, real-life experience, and investment. We’re now ready on all three levels, so it’s an exciting time.
More formal info to come.
[quote quote=7887]Doesn’t a greater number of trades reduce returns due to fees?[/quote]
I am of the hope that the models are designed with trade fees in mind, but I am sure they already considered fees as a major factor in determining how well the models perform in the long term. Also, FTX exchange has a spot market fee of 0.07% compared to Binance’s 0.1%. Maybe the team can consider adding support for FTX as a way to reduce fees incurred from greater number of trades.
- You must be logged in to reply to this topic.