D3M - Data-Driven Discovery of Models

The Data-Driven Discovery of Models (D3M) program aims to develop automated model discovery systems that enable users with subject matter expertise but no data science background to create empirical models of real, complex processes. ## Key Components - **AlphaD3M**: Machine learning pipeline synthesis using reinforcement learning - **d3m-interface**: Python library for integrating D3M AutoML systems with Jupyter Notebooks - **PipelineProfiler**: Visual analytics tool for exploring AutoML pipelines ## Related Publications - Roque Lopez, Raoni Lourenco, Remi Rampin, Sonia Castelo, Aecio Santos, Jorge Piazentin Ono, Claudio Silva, Juliana Freire. "AlphaD3M: Machine Learning Pipeline Synthesis and AutoML" - Jorge Ono, Sonia Castelo, Roque Lopez, Enrico Bertini, Juliana Freire, Claudio Silva. "PipelineProfiler: A Visual Analytics Tool for the Exploration of AutoML Pipelines"