Towards AI

DECEMBER 19, 2023

It is very risky to apply these black-box AI systems in real-life applications, especially in sectors like banking and healthcare. For example, a deep neural net used for a loan application scorecard might deny a customer, and we will not be able to explain why. arXiv: 2003.07132 where n is the sample size.

Neural Network 110

Neural Network AI Modeling Black Box AI Explainability 110

ODSC - Open Data Science

APRIL 4, 2023

Transparency The lack of transparency in many AI models can also cause issues. Users may not understand how these systems work and it can be difficult to figure out, especially with black-box AI. Being unable to resolve things could lead businesses to experience significant losses from unreliable AI applications.

Black Box AI 98

Black Box AI AI AI Data Science 98

Unite.AI

APRIL 9, 2024

The adoption of Artificial Intelligence (AI) has increased rapidly across domains such as healthcare, finance, and legal systems. However, this surge in AI usage has raised concerns about transparency and accountability. Composite AI is a cutting-edge approach to holistically tackling complex business problems.

Composite AI 182

Composite AI Explainability Black Box AI Explainable AI 182

DataRobot Blog

NOVEMBER 3, 2022

It takes something that’s hard to do but important to get right — forecasting — and supercharges data scientists. With automated feature engineering, automated model development, and more explainable forecasts, data scientists can build more models with more accuracy, speed, and confidence. Forecasting the future is difficult.

Data Scientist 52

Data Scientist Black Box AI Explainability Automation 52