Transparent, Robust and Ultra-Sparse Trees (TRUST)

TRUST is my flagship Ph.D. project in Trustworthy AI. It achieves comparable accuracy to high-performing machine learning algorithms - including black box models like Random Forest - while remaining fully interpretable. Scroll down for a short demo of TRUST. Current version solves multiclass classification and regression problems, including time series (experimentally).

For further details and documentation, please visit the project’s GitHub repository.

Below is a demo of the integrated LLM capabilities within TRUST (in the beta/dev version). The video starts by showing the call to the .explain() method, where a user wishes to know more about the model’s prediction for a specific instance (a target house). After the default output is shown, including the key features influencing the prediction and their direction, plus a final summary explanation, the user then asks Gemini a completely custom question: what minimum changes should be made in the attributes of the given house for the model to output a cheaper predicted price instead? This demonstrates the potential for actionable insights and counterfactual analysis offered by LLM integration.