Overview

Add a model by clicking on the top-left button. Once you model saved, it will be displayed on your model dashboard.

Name

Each model has a name. Model names must be unique. By default you are provided a random model name.

Algorithm

Each model uses an algorithm. Algortihms currently available :

• Classification (SVM)

LSTM will be released soon. You must configure your model according to the algorithm you choose.

Data provider

The data your model is trained on. Sources currently available:

• Alpaca
• Binance

You must be aware of the difference between how your model is trained and the exchange it is running on.

Asset

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).

Period

The time series period (historical data) your model will be trained on.

Interval

The interval between each data point.

Features

There is currently 2 types of features :

• OHLCV : Data related to Open, High, Low, Close and Volume metrics.
• Technical indicators : All the indicators from the TA-Lib library.

Training set

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

Kernel hyperparamter of your model, RBF by default.

C

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

Gamma hyperparamter of your model, you can add and and delete how many values you want. The best Gamma value will be automatically chosen.

Training and backtest

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.