Bitcoin neural network analysis week 29/2019: Still undecided

Analysis of past week:
The network did expect a correction and last week started exactly as planned. But then we recovered relatively quickly and nothing much happened after that. The network strategy was not ideal.

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%: 16478.75$ (up 0.5 %)
Holding BTC: 10589.71$ (up 3 %)
Network strategy: 11106.28$ (up 0.5 %)
Starting capital: 11497.40$

The neural network has gotten a small edge above holding bitcoin. Fiat with 30% annual interest is still preferred.

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 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 does not foresee any relevant moves. That does not mean that nothing will happen. It simply means that the network sees equal opportunities for moves up and moves down. The network is therefore very much undecided.

The network slightly prefers fiat over bitcoin for the next week, so the strategy will be sitting on fiat for now.

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!