Add a model by clicking on the top-left button. Once your model is 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:
Size of the candlesticks of the dataset.
The time series period (historical data) your model will be trained on.
You model must be trained on data from one asset at a time. It lists only shortable stocks for Alpaca. Stocks are printed as <Company Legal Name> <TICKER> and FX & cryptos as <BASE/QUOTE>
There is currently 2 types of features :
For medium, the model classifies as "BUY" returns higher than 66% of the distribution, and "SELL" those lower than 33%.
For low, respectively 56% and 44%.
For high, respectively 85% and 14%.
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 hyperparameter of your model, RBF by default. More info about kernels : https://scikit-learn.org/stable/auto_examples/svm/plot_svm_kernels.html
C hyperparameter of your model, you can add and and delete how many values you want. The best C value will be automatically chosen. "The C parameter trades off correct classification of training examples against maximization of the decision function’s margin." More info about C parameter : https://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html
Gamma hyperparameter of your model, you can add and and delete how many values you want. The best Gamma value will be automatically chosen. "Intuitively, the gamma parameter defines how far the influence of a single training example reaches, with low values meaning 'far' and high values meaning 'close'." More info about Gamma parameter : https://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html
Once your model is saved, you can see its name, its status ("trained", "not trained", "training" or "error") and you can review all its details in the parameters section. Make sure all these details are correct. If not, you can delete the model by clicking on the bin icon and typing your model's name. If details are correct, you can go to the next step.
To start the process, simply click on the loading icon and click on the "start backtesting" button. After that, your model's status must become "training" and you will be invited to go to the chat section to be notified when your model is ready.
Each model's report is made of 4 elements:
The graph is composed of two lines: one yellow and one black. The yellow one represents the cumulative historical returns of the model's strategy. The black one represents the cumulative historical returns of the asset.
To make it simple, it shows the accuracy of your model. More info about classification report : https://scikit-learn.org/stable/modules/model_evaluation.html#classification-report
An image that shows the difference between the prediction and the actual values. The Y axis is the prediction and X is the actual values. More info about the confusion matrix : https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html
Add a trading bot by clicking on the top-left button. Once your trading bot is 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. Only trained models are available.
Choose the broker / exchange on which the bot will be running.
Choose between live and paper trading.
API keys of your broker exchange according to your mode.
Choose at which frequency the bot will take a decision among : "BUY", "SELL" and "HOLD".
Amount of asset the bot will buy/sell for each trade.
Once your bot is saved, you can see its name, its status ("running" or "not running") and you can review all its details in the parameters section. Make sure all these details are correct. If not, you can delete the bot by clicking on the bin icon and typing your bot's name. If details are correct, you can go to the next step.
Start (or stop) the bot by clicking on the power on/off icon. Wait a few seconds for the bot to start.
The 20 last decisions and events concerning the bot are stored in this real-time logs section.
The 20 last opened / closed positions are displayed on this real-time graph.
The dashboard allows you to have a quick look at all your models / bots and how they are performing within the last 20 candlesticks in real-time. Each model contains all of its attached bots. Each bot shows their performance (green for positive, red for negative) and the model shows the average performance of all its attached bots.
Let's see what are the differences between the Free and the Premium plan. So, the Free and the Premium plans are the same except on the following points :
Free plans have a maximum of 20 features. Premium plans have not limit.
Premium plans send and receive messages via chat. Free plans can only receive messages.