What is the process for implementing a shifted moving average applied on an RSI and incorporating the crossover as a hyperparameter in my machine learning algorithm?
Hello Mark,
Could you provide more details about your ML algorithm to facilitate a more precise response to your question? What is the primary objective of your ML algorithm, and could you share information about the type of ML model?
Regarding the use of crossover as a hyperparameter, typically, the approach may vary based on the machine learning framework employed. However, it is generally necessary to make adjustments to your model architecture to accommodate these hyperparameters.
For instance, if you are utilising a neural network, you might designate a hyperparameter for the bullish crossover threshold and another for the bearish crossover threshold. These hyperparameters could be integrated into the model's input layer or utilised to dynamically adjust the model's behaviour during training.
In the training process, consider employing a hyperparameter optimisation technique to determine the optimal values for your crossover thresholds. This may involve methods such as grid search or random search.
For each set of hyperparameters, including crossover thresholds, proceed to train the model and evaluate its performance on a validation set. The optimisation algorithm will iterate over various combinations of hyperparameters, ultimately selecting the set that maximises your chosen performance metric (e.g., accuracy, profit, etc.).
I hope this helps!