Add a model by clicking on the top-left button. Once you model saved, it will be displayed on your model dashboard.
Each model has a name. Model names must be unique. By default you are provided a random model name.
Each model uses an algorithm. Algortihms currently available :
The data your model is trained on. Sources currently available:
You model must be trained on data from one asset at a time. It lists only shortable stocks for Alpaca. You can update this list every 5 minutes (the data is fetched directly from Alpaca).
The time series period (historical data) your model will be trained on.
The interval between each data point.
There is currently 2 types of features :
Split point (%) between the training set and the test set. If the training set is x%, the test set will be (100-x)% automatically.
Kernel hyperparamter of your model, RBF by default.
C hyperparamter of your model, you can add and and delete how many values you want. The best C value will be automatically chosen.
Gamma hyperparamter of your model, you can add and and delete how many values you want. The best Gamma value will be automatically chosen.
Once you model saved, you can train and backtest it. If your model is correctly built, it will display a graph with 2 lines. If not, you will be prompted an error message. Each graph is made of two lines : the cumulative returns of the model and the market. You can compare them to choose between keeping or modifying your model.
Add a trading bot by clicking on the top-left button. Once you trading bot saved, it will be displayed on your trading bots dashboard.
Each trading bot has a name. Trading bot names must be unique. By default you are provided a random trading bot name.
Each trading bot must be attached to a model. You can attach multiple bots to a single model. You must provided only and all the models your created.