We're going deep! The Deep Signal Library v1.7 allows users to send and receive data from the Deep Signal Library to/from Python. This allows users to create deep learning models in Python and use those models to send trading signals to NinjaTrader.
Thrilled to announce the release of the Deep Signal Library 1.6. It adds powerful new features for creating financial machine learning models including Feature Importance, Dataset Weights and Trainer Customization for tuning hyper-parameters.
Deep Signal Technologies is excited to announce the release of the Deep Signal Library 1.5. The new version includes Regression and Multiclass machine learning trainers for creating new financial trading models with NinjaTrader.
In addition, we've added a confidence score to the prediction methods that will return a number (0.0-1.0) that the user can use to make trading entry decisions.
The Deep Signal Library can now use multiple machine learning models in one NinjaTrader strategy. Want to create multiple models for different market conditions or use multiple models for triggers to enter a trade? The latest Deep Signal Library provides a source code example of how to integrate multiple machine learning models in your strategy.
Deep Signal now gives you more insight into your machine learning models for trading. You can easily view long and short trade entries your trained ML model would make in your NinjaTrader Chart using Deep Signal Indicators.
The Deep Signal Library version 1.3 has been released. Several new features including the ability to choose trainers for creating machine learning models as well as a new updated progress dialog for creating models.
New videos have been added to help with installing and using the Deep Signal Library. Please check out our YouTube Channel for help with creating new machine learning models, using the models for live trading and installing the Deep Signal Library.