Bitcoin neural network analysis week 12/2019: Retesting 4000 and failing

Analysis of past week:
The network was very pessimistic last week, but we saw a quick rise to the 4000$ level. The network strategy was suboptimal.

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%: 15063.81$ (up 0.5 %)
Holding BTC: 4025.23$ (up 1.9%)
Network strategy: 4279.64$ (up 0.5%)
Starting capital: 11497.40$

The fiat strategy is up since the documented time has been a bear market. The neural network has gotten some edge above holding bitcoin.

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 expects that we retest the 4100$ region but ultimately fail to break this critical resistance. After that the direction is down retesting the previous lows. The good news for the bulls is however that if we should break 4300$, there is very little resistance left until the 5000-6000$. Very interesting times are ahead.

Since the network is pessimistic, the strategy remains holding fiat with a 0.5% interest.

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!