Machine learning explainability refers to the ability to understand and interpret the reasoning behind the predictions made by a machine learning model. It is important for ensuring transparency and accountability in the decision-making process. Explainable AI techniques, such as feature importance analysis and model interpretability, help to provide insights into how a model arrives at its output. This can help to detect and prevent bias, increase trust in AI systems, and facilitate regulatory compliance. Model insights, also known as model interpretability or explainability, refer to the ability to understand how a machine learning model works and why it makes certain predictions or decisions.

Deloitte AI Institute announced Monday a new partnership with Chatterbox Labs to develop Model Insights for Trustworthy AI, a Deloitte-branded product that will assist organizations address artificial intelligence (AI) ethics by monitoring, updating, and validating clients' AI models. Through our collaboration with Chatterbox Labs, our Model Insights technology solution can help our clients put the Trustworthy AI framework into action and mitigate the ethical risks associated with AI," commented Beena Ammanath, executive director of Deloitte AI Institute. Deloitte discovered in its "State of AI in the Enterprise" third edition study of AI adopters that 95% of respondents were concerned about ethical implications. In response to the survey, Deloitte created its Trustworthy AI framework, which will guide clients on how to use AI in their business models responsibly and effectively. Model Insights will recognize immediate insights and unaccounted for biases which will allow clients to be sure their AI models are ethical and fair. Deloitte's Model Insights solution is built on Artificial Intelligence Model Insights (AIMI) from Chatterbox Labs. This patented platform delivers data and insights into enterprise AI models, enabling organizations to validate and understand their AI initiatives and ensure they are operating fairly and ethically. "Our collaboration with the Deloitte AI Institute will provide Deloitte clients with deep insights into how their AI models are operating so that they can mitigate ethical risks and validate their systems are trustworthy and fair," said Danny Coleman, CEO of Chatterbox Labs. Deloitte and Chatterbox's collaboration can impact a wide variety of organizations that are rapidly adopting AI technology, such as financial services, government, public sector, life sciences and healthcare. Model Insights for Trustworthy AI could provide those organizations with a deep AI experience with an ethical framework. "Rapid developments in AI have unlocked incredible opportunities for organizations globally.

Silas: High Performance, Explainable and V erifiable Machine Learning Hadrien Bride, Zh e H ou Griffith University, Nathan, Brisbane, Australia Jie Dong Dependable Intelligence Pty Ltd, Brisbane, Australia Jin Song Dong National University of Singapore, Singapore Ali Mirjalili Griffith University, Nathan, Brisbane, AustraliaAbstract This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service. A focus of Silas is on providing a formal foundation of decision trees in order to support logical analysis and verification of learned prediction models. This paper describes the distinct features of Silas: The Model Audit module formally verifies the prediction model against user specifications, the Enforcement Learning module trains prediction models that are guaranteed correct, the Model Insight and Prediction Insight modules reason about the prediction model and explain the decision-making of predictions. We also discuss implementation details ranging from programming paradigm to memory management that help achieve high-performance computation.1. Introduction Machine learning has enjoyed great success in many research areas and industries, including entertainment [1], self-driving cars [2], banking [3], medical diagnosis [4], shopping [5], and among many others. However, the wide adoption of machine learn-Preprint submitted to Elsevier October 4, 2019 arXiv:1910.01382v1 The ramifications of the black-box approach are multifold. First, it may lead to unexpected results that are only observable after the deployment of the algorithm. For instance, Amazon's Alexa offered porn to a child [6], a self-driving car had a deadly accident [7], etc. Some of these accidents result in lawsuits or even lost lives, the cost of which is immeasurable. Second, it prevents the adoption in some applications and industries where an explanation is mandatory or certain specifications must be satisfied. For example, in some countries, it is required by law to give a reason why a loan application is rejected. In recent years, eXplainable AI (XAI) has been gaining attention, and there is a surge of interest in studying how prediction models work and how to provide formal guarantees for the models. A common theme in this space is to use statistical methods to analyse prediction models.