AI Crypto Trading
DipSway's powerful AI bot dynamically adapts to the rapid market changes. All of this is done through a series of steps:
Imagine a neural network as a black box that takes in a set of inputs and produces a set of outputs.
The inputs are the features of the data, and the outputs are the signals made by the model
The model is trained by adjusting the weights of the connections between the neurons.
The weights are adjusted by using a scoring function to determine how well/poorly the trading strategy is performing. In particular fields such as average profit, average loss, win rate, avg. trade-duration, etc... are used to calculate the loss.
The scoring function is then used to calculate the gradient of the win/loss with respect to the weights.
The gradient is then used to update the weights.
This process is repeated until the model is trained.
The model is then used to make "predictions" on new data.
The model is then re-trained every 24h using an Online Learning approach.
A GRAPHICAL REPRESENTATION
What's behind the scenes?
In the image, some of the indicators are showing a potential buy signal (green), while others are showing a potential sell signal (red). The neural network takes all of these indicators into account and makes a decision based on the overall picture, producing a single buy or sell signal.
Why we need a Neural Network?
Reasons why other trading strategies fail:
- Based on a single indicator
- Not backtested properly
- Not optimized for the current market conditions
- Not self-evolving and self-learning