FICO, Google, UC Berkeley and Oxford University are among the sponsors of a major new contest aimed at providing a high profile public example of progress with XAI.
The challenge is not fully ready for contestants to dig in yet. However, explainable.ml has a preview and a link to get you on the list.
When business decisions are made based on artificial intelligence, machine learning and algorithmic models, there is a need to provide a clear explanation of why and how that particular decision was made. This not only helps human users understand and trust the decision, it is often required due to regulatory and compliance constraints.
The Explainable Machine Learning Challenge is designed to encourage continued research and innovation in making machine learning algorithms more explainable and to expand the set of explainable AI methods used today. Without explanations, these algorithms often cannot meet regulatory requirements, human scrutiny, or customer expectations.
Teams will be challenged to create machine learning models with both high accuracy and correct explanations, using a real-world dataset provided by FICO.