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!
Analysis of past week:
The network did predict a quite bad week, but then the past week became a somewhat calm but positive week for bitcoin.
The network prediction was not that far of the truth, but the decision based on the network turned out to be suboptimal. This can and will happen often as the network only finds small trends on top of a big random noise.
I am comparing three strategies, first hold fiat and make a small profit elsewhere, hold bitcoin or follow the network predictions. For last week due to the bad forecast this meant exposure to fiat. Since I started documenting my predictions on the blockchain these strategies compare as
Fiat with a weekly profit of 0.5%: 11670.72$
Holding BTC: 8495.78$
Network strategy: 9674.65$
Note that the fiat strategy is up since the entire documented time has been a bear market. The neural network has gained an upper hand over btc but it is too early to tell if that was just luck or good analysis.
Forecast:
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 black line is one week into the future. The network prediction is smooth as the random noise is filtered out.
This week the network prediction is much friendlier. The network sees a solid growth in the beginning of the week, followed by a shortlived pullback towards the easter weekend with a target of 8500.36$. The forecast for the later month is positive.
This week, due to the expected pullback, both strategies are very close together. The network prefers exposure to fiat with a 0.5% growth by a very small bit, so my strategy for the coming week is once again holding fiat.
