Science

A new study rigorously evaluates seven neural network architectures to find the best balance between precision and diversity in e-commerce recommendation systems.

A new study explores whether framing AI evaluation as a prediction game can reveal more accurate confidence levels and accelerate learning.

New research reveals how detrended cross-correlation methods, combined with random matrix theory, can untangle the complex relationships within cryptocurrency markets.

New research leverages topic modeling to uncover hidden connections between hedge fund communications and actual investment performance.

New research shows artificial intelligence can significantly improve strategies for managing risk in complex interest rate derivative markets.

A new technique allows large language models to selectively ‘unlearn’ information during use, improving reliability and opening doors for deployment in critical fields.

Artificial intelligence is rapidly transforming anti-money laundering practices, offering the potential for more accurate, efficient, and transparent financial systems.

A new study demonstrates how convolutional neural networks can identify and explain potentially fraudulent activity in publicly traded companies.

New research reveals that background distractions in images don’t always hinder deep learning models for autonomous vehicle perception, challenging conventional assumptions about feature importance.

A new approach tackles the challenges of zero-shot super-resolution forecasting by enabling models to generalize effectively across different resolutions.