dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
This tool helps machine learning practitioners and researchers manage risks like discrimination and lack of reproducibility in black-box models, addressing a critical need driven by scientific, social, and regulatory demands.
The dalex Python package provides a model-agnostic interface for interactive model exploration to address the opaqueness of complex predictive models. It aims to unify existing solutions for responsible machine learning by facilitating better validation of model performance and fairness, higher explainability, and continuous monitoring.
The increasing amount of available data, computing power, and the constant pursuit for higher performance results in the growing complexity of predictive models. Their black-box nature leads to opaqueness debt phenomenon inflicting increased risks of discrimination, lack of reproducibility, and deflated performance due to data drift. To manage these risks, good MLOps practices ask for better validation of model performance and fairness, higher explainability, and continuous monitoring. The necessity of deeper model transparency appears not only from scientific and social domains, but also emerging laws and regulations on artificial intelligence. To facilitate the development of responsible machine learning models, we showcase dalex, a Python package which implements the model-agnostic interface for interactive model exploration. It adopts the design crafted through the development of various tools for responsible machine learning; thus, it aims at the unification of the existing solutions. This library's source code and documentation are available under open license at https://python.drwhy.ai/.