Bitcoin neural network analysis week 20/2019: Short squezzed
Analysis of past week:
Last week was probably the craziest week we have seen in a long while. Bitcoin smashed 6000$, then 6400$, then 7000$ and even climbed somewhat higher after. Especially the 6400$ is crucial as we are again above the previous support levels.
The network was optimistic for the last week but obviously did not expect such a rally. Nevertheless the network strategy was optimal.
I am comparing three strategies, first hold fiat and make a small profit elsewhere, hold bitcoin, or follow the network predictions. Since I started documenting my predictions on the blockchain these strategies compare as
Fiat with a weekly profit of 0.5%: 15677.02$ (up 0.5 %)
Holding BTC: 6972.37$ (up 20.3 %)
Network strategy: 7493.07$ (up 20.3 %)
Starting capital: 11497.40$
The fiat strategy is up since most of the documented time has been a bear market. The neural network has gotten some edge above holding bitcoin.
Forecast:
.png)
Red areas are predicted below the current price, blue/yellow areas indicate the expected passive growth, green areas are better than the expected growth. The vertical line is one week into the future and its size provides the prediction variance. The network prediction is smooth as the random noise is filtered out.
The network forecast is close the most reasonable bullish outlook. It expects that we first consolidate around the 7000$, then make a new higher low at the 6400$ support and then climb higher from there. This sounds very reasonable, the main question seems to be just when we make the higher low and how low it will be.
And this time, the network variance is very large, meaning that we may see significant drops already this week, but the network slightly prefers rising prices before a significant drop.
Since the network is positive for the coming week, the strategy remains to hold bitcoin over fiat.
This post is not financial advice! I am testing the potential to use neural networks for price predictions and am documenting my results on the blockchain to have provable public results. All prices are based on 0:00 UTC for consistency!
Did you mention earlier which are the criteria on how the network is speculating? I have no clue on what this is build on. I'm simply impressed how accurate it is working.
Greets
Posted using Partiko Android
The network is trained on past price data since 2014 and is looking at the prices of the past 100 days to estimate the price of tomorrow.
Internally it is a black-box and I have no idea how it is coming up with the numbers. But here is a useful plot
.png)
These are normalised relative price changes in the training sample in blue and the network prediction in orange. It is immediately clear that they differ a lot and the network does not perfectly predict the price at all. But there is still a clear correlation between the two curves so that the network does predict a small hint.
Okay, I see now what is the black-box and network. How does the training looks like? The network gets a training sample and reacts according to which principal? Is there a scalation?
Posted using Partiko Android
The network is training on past data trying to minimise the post-diction error.
Okay. I guess to see now the intuition in it.
Thanks for the post✌️
Greets
Posted using Partiko Android
Congratulations! This post has been upvoted from the communal account, @minnowsupport, by frdem3dot0 from the Minnow Support Project. It's a witness project run by aggroed, ausbitbank, teamsteem, someguy123, neoxian, followbtcnews, and netuoso. The goal is to help Steemit grow by supporting Minnows. Please find us at the Peace, Abundance, and Liberty Network (PALnet) Discord Channel. It's a completely public and open space to all members of the Steemit community who voluntarily choose to be there.
If you would like to delegate to the Minnow Support Project you can do so by clicking on the following links: 50SP, 100SP, 250SP, 500SP, 1000SP, 5000SP.
Be sure to leave at least 50SP undelegated on your account.
@frdem3dot0 Thank you for not using bidbots on this post and also using the #nobidbot tag!
Hi @frdem3dot0!
Your post was upvoted by @steem-ua, new Steem dApp, using UserAuthority for algorithmic post curation!
Your UA account score is currently 3.896 which ranks you at #3971 across all Steem accounts.
Your rank has improved 35 places in the last three days (old rank 4006).
In our last Algorithmic Curation Round, consisting of 172 contributions, your post is ranked at #110.
Evaluation of your UA score:
Feel free to join our @steem-ua Discord server